Clinical Benchmarks

MedScribe (Vals AI)

Quality and compliance of SOAP notes generated from clinical visits, scored against documentation rubrics.

More about this boardLess

Clinical documentation support: quality of SOAP notes generated from clinical visits, scored against rubrics for documentation quality and compliance.

Vals AI self-runs; 105 models on the board, last updated September 29, 2026. Top scores cluster near 90, so the leaders sit close to the ceiling.

Published by Vals AI (dataset with Protege), released Feb 2026. 100 rubric-scored SOAP-note cases. Percentage accuracy 0-100, higher better.

Rows on the board
105
Board last updated
29 Sep 2026
Publisher
Vals AI (dataset with Protege)
Rows
106
Models
95 of 105 on the board
Released
Feb 2026
Measured to
Oct 2026
Unit
100 SOAP-note cases
Documents cited
2

Every result on MedScribe (Vals AI), on the board's own scale

106 results, one column each, highest first. Percentage accuracy 0-100, higher better.

Column colour is the model's lab. The table below says who ran each result.

Every published result, ranked on this board alone

106 rows. Higher is better. Bars run from 0 to 100; whiskers show a published interval. Select a row for its quote, page and document.

1Claude Opus 5.5Anthropic · claude-opus-5-591.43Board publisherSep 2026[1]
1 | Claude Opus 5.5 | 91.43%±1.93 | $4/$20 | 7m22s
As printed
91.43%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 1 of 105 (Claude Opus 5.5), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-opus-5-5"].
Setting
model ID anthropic/claude-opus-5-5; temperature=1; max_output_tokens=128000; compute_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
2Claude Fable 5.1Anthropic91.29Board publisherSep 2026[1]
2 | Claude Fable 5.1 | 91.29%±1.95 | $10/$50 | 3m08s
As printed
91.29%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 2 of 105 (Claude Fable 5.1), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-fable-5-1"].
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
3Claude Sonnet 5.5Anthropic · claude-sonnet-5-591.10Board publisherSep 2026[1]
3 | Claude Sonnet 5.5 | 91.10%±1.96 | $2/$10 | 5m07s
As printed
91.10%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 3 of 105 (Claude Sonnet 5.5), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-sonnet-5-5"].
Setting
model ID anthropic/claude-sonnet-5-5; temperature=1; max_output_tokens=128000; compute_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
4Claude Opus 5Anthropic90.98Board publisherSep 2026[1]
4 | Claude Opus 5 | 90.98%±1.92 | $5/$25 | 76.56s
As printed
90.98%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 4 of 105 (Claude Opus 5), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-opus-5"].
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
5Muse Spark 1.2Meta90.06Board publisherSep 2026[1]
5 | Muse Spark 1.2 | 90.06%±1.96 | $1.25/$4.25 | 61.46s
As printed
90.06%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 5 of 105 (Muse Spark 1.2), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["meta/muse_spark_1_2"].
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
6Grok 4.7SpaceX AI · grok-4.789.38Board publisherSep 2026[1]
6 | Grok 4.7 | 89.38%±1.89 | $2/$6 | 2m33s
As printed
89.38%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 6 of 105 (Grok 4.7), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["grok/grok-4.7"].
Setting
model ID grok/grok-4.7; temperature=1; top_p=0.95; reasoning_effort=xhigh
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
7GLM 5.3 FlashZhipu · glm-5.3-flash88.94Board publisherSep 2026[1]
7 | GLM 5.3 Flash | 88.94%±1.91 | $0.075/$0.25 | 86.98s
As printed
88.94%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 7 of 105 (GLM 5.3 Flash), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["zai/glm-5.3-flash"].
Setting
model ID zai/glm-5.3-flash; temperature=1; top_p=0.95; max_output_tokens=30000; reasoning_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
8Muse Spark 1.1Meta88.89Board publisherSep 2026[1]
8 | Muse Spark 1.1 | 88.89%±1.95 | $1.25/$4.25 | 63.34s
As printed
88.89%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 8 of 105 (Muse Spark 1.1), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["meta/muse_spark_1_1"].
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
9GLM 5.3Zhipu · glm-5.388.81Board publisherSep 2026[1]
9 | GLM 5.3 | 88.81%±2.00 | $1.4/$4.4 | 2m02s
As printed
88.81%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 9 of 105 (GLM 5.3), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["zai/glm-5.3"].
Setting
model ID zai/glm-5.3; temperature=1; top_p=0.95; max_output_tokens=30000; reasoning_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
10Claude Fable 5Anthropic88.52Board publisherSep 2026[1]
10 | Claude Fable 5 | 88.52%±1.95 | $10/$50 | 119.47s
As printed
88.52%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 10 of 105 (Claude Fable 5), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-fable-5"].
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
11MiMo V2.6 ProXiaomi · mimo-v2.6-pro88.31Board publisherSep 2026[1]
11 | MiMo V2.6 Pro | 88.31%±1.94 | $0.435/$0.87 | 2m53s
As printed
88.31%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 11 of 105 (MiMo V2.6 Pro), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["xiaomi/mimo-v2.6-pro"].
Setting
model ID xiaomi/mimo-v2.6-pro; temperature=1; top_p=0.95; max_output_tokens=128000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
12GPT 5.1OpenAI88.09Board publisherSep 2026[1]
12 | GPT 5.1 | 88.09%±1.94 | $1.25/$10 | 77.98s
As printed
88.09%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 12 of 105 (GPT 5.1), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-5.1-2025-11-13"].
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
13Kimi K3Moonshot AI87.96Board publisherSep 2026[1]
13 | Kimi K3 | 87.96%±1.89 | $3/$15 | 2m17s
As printed
87.96%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 13 of 105 (Kimi K3), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["kimi/kimi-k3"].
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
14GPT-6 AstraOpenAI87.91Board publisherSep 2026[1]
14 | GPT-6 Astra | 87.91%±1.94 | $10/$50 | 2m34s
As printed
87.91%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 14 of 105 (GPT-6 Astra), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-6-astra"].
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
15Gemini 4 ArgonGoogle87.43Board publisherOct 2026[2]
Weaker on MedScribe (87.43%, #15 of 106) and CUA-bench (4.83%, #7 of 8).
As printed
87.43%
Where
Vals AI model page for Gemini 4 Argon, summary bullets, fifth bullet. The MedScribe leaderboard page did not render its table in the crawl.
Reported by
official leaderboard
Document
[2] Vals AI: Gemini 4 Argon model page
16MiniMax-M3MiniMax87.25Board publisherSep 2026[1]
15 | MiniMax-M3 | 87.25%±1.96 | $0.6/$2.4 | 2m04s
As printed
87.25%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 15 of 105 (MiniMax-M3), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["minimax/MiniMax-M3"].
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
17Grok 4.5SpaceX AI · grok-4.586.88Board publisherSep 2026[1]
16 | Grok 4.5 | 86.88%±1.94 | $2/$6 | 11m45s
As printed
86.88%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 16 of 105 (Grok 4.5), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["grok/grok-4.5"].
Setting
model ID grok/grok-4.5; temperature=1; top_p=0.95; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
18GPT 5.5OpenAI86.87Board publisherSep 2026[1]
17 | GPT 5.5 | 86.87%±1.93 | $5/$30 | 2m13s
As printed
86.87%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 17 of 105 (GPT 5.5), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-5.5"].
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
19Claude Opus 4.6 (Nonthinking)Anthropic86.74Board publisherSep 2026[1]
18 | Claude Opus 4.6 (Nonthinking) | 86.74%±1.94 | $5/$25 | 54.32s
As printed
86.74%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 18 of 105 (Claude Opus 4.6 (Nonthinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-opus-4-6"].
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
20Grok 4.6SpaceX AI86.53Board publisherSep 2026[1]
19 | Grok 4.6 | 86.53%±1.96 | $2/$6 | 70.94s
As printed
86.53%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 19 of 105 (Grok 4.6), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["grok/grok-4.6"].
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
21GPT-6.1 SolOpenAI · gpt-6.1-sol86.45Board publisherSep 2026[1]
20 | GPT-6.1 Sol | 86.45%±1.90 | $2/$10 | 2m50s
As printed
86.45%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 20 of 105 (GPT-6.1 Sol), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-6.1-sol"].
Setting
model ID openai/gpt-6.1-sol; max_output_tokens=128000; reasoning_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
22Claude Opus 4.6 (Thinking)Anthropic · claude-opus-4-6-thinking86.13Board publisherSep 2026[1]
21 | Claude Opus 4.6 (Thinking) | 86.13%±1.94 | $5/$25 | 2m08s
As printed
86.13%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 21 of 105 (Claude Opus 4.6 (Thinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-opus-4-6-thinking"].
Setting
model ID anthropic/claude-opus-4-6-thinking; temperature=1; max_output_tokens=30000; compute_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
23Muse SparkMeta · muse_spark85.90Board publisherSep 2026[1]
22 | Muse Spark | 85.90%±1.85 | N/A | 3m11s
As printed
85.90%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 22 of 105 (Muse Spark), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["meta/muse_spark"].
Setting
model ID meta/muse_spark; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
24Claude Opus 4.8Anthropic · claude-opus-4-885.75Board publisherSep 2026[1]
23 | Claude Opus 4.8 | 85.75%±1.93 | $5/$25 | 82.36s
As printed
85.75%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 23 of 105 (Claude Opus 4.8), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-opus-4-8"].
Setting
model ID anthropic/claude-opus-4-8; temperature=1; max_output_tokens=30000; compute_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
25DeepSeek V4.1 FlashDeepSeek · deepseek-v4.1-flash85.50Board publisherSep 2026[1]
24 | DeepSeek V4.1 Flash | 85.50%±1.92 | $0.3/$1.2 | 53.83s
As printed
85.50%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 24 of 105 (DeepSeek V4.1 Flash), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["deepseek/deepseek-v4.1-flash"].
Setting
model ID deepseek/deepseek-v4.1-flash; max_output_tokens=384000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
26InklingThinking Machines · inkling85.41Board publisherSep 2026[1]
25 | Inkling | 85.41%±1.84 | $1/$4.05 | 4m05s
As printed
85.41%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 25 of 105 (Inkling), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["thinkingmachines/inkling"].
Setting
model ID thinkingmachines/inkling; temperature=1; top_p=1; max_output_tokens=30000; reasoning_effort=0.99
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
27Claude Opus 4.5 (Thinking)Anthropic · claude-opus-4-5-20251101-thinking85.32Board publisherSep 2026[1]
26 | Claude Opus 4.5 (Thinking) | 85.32%±1.90 | $5/$25 | 72.11s
As printed
85.32%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 26 of 105 (Claude Opus 4.5 (Thinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-opus-4-5-20251101-thinking"].
Setting
model ID anthropic/claude-opus-4-5-20251101-thinking; temperature=1; max_output_tokens=30000; compute_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
28MiMo V2.6 FlashXiaomi · mimo-v2.6-flash85.28Board publisherSep 2026[1]
27 | MiMo V2.6 Flash | 85.28%±1.99 | $0.14/$0.28 | 74.48s
As printed
85.28%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 27 of 105 (MiMo V2.6 Flash), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["xiaomi/mimo-v2.6-flash"].
Setting
model ID xiaomi/mimo-v2.6-flash; temperature=1; top_p=0.95; max_output_tokens=128000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
29Claude Haiku 4.5 (Thinking)Anthropic · claude-haiku-4-5-20251001-thinking85.23Board publisherSep 2026[1]
29 | Claude Haiku 4.5 (Thinking) | 85.23%±1.90 | $1/$5 | 66.20s
As printed
85.23%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 29 of 105 (Claude Haiku 4.5 (Thinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-haiku-4-5-20251001-thinking"].
Setting
model ID anthropic/claude-haiku-4-5-20251001-thinking; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
29GPT-5.6 SolOpenAI · gpt-5.6-sol85.23Board publisherSep 2026[1]
28 | GPT-5.6 Sol | 85.23%±1.97 | $4/$20 | 94.40s
As printed
85.23%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 28 of 105 (GPT-5.6 Sol), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-5.6-sol"].
Setting
model ID openai/gpt-5.6-sol; max_output_tokens=30000; reasoning_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
31Qwen 3.8 MaxAlibaba · qwen3.8-max84.95Board publisherSep 2026[1]
30 | Qwen 3.8 Max | 84.95%±2.00 | $2/$6 | 4m11s
As printed
84.95%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 30 of 105 (Qwen 3.8 Max), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["alibaba/qwen3.8-max"].
Setting
model ID alibaba/qwen3.8-max; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
32Claude Sonnet 4.5 (Nonthinking)Anthropic · claude-sonnet-4-5-2025092984.52Board publisherSep 2026[1]
31 | Claude Sonnet 4.5 (Nonthinking) | 84.52%±1.93 | $3/$15 | 44.42s
As printed
84.52%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 31 of 105 (Claude Sonnet 4.5 (Nonthinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-sonnet-4-5-20250929"].
Setting
model ID anthropic/claude-sonnet-4-5-20250929; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
33Gemini 3.8 FlashGoogle · gemini-3.8-flash84.50Board publisherSep 2026[1]
32 | Gemini 3.8 Flash | 84.50%±1.94 | $1.5/$7.5 | 21.14s
As printed
84.50%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 32 of 105 (Gemini 3.8 Flash), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-3.8-flash"].
Setting
model ID google/gemini-3.8-flash; temperature=1; max_output_tokens=65536; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
34GPT 5.2OpenAI · gpt-5.2-2025-12-1184.39Board publisherSep 2026[1]
34 | GPT 5.2 | 84.39%±1.86 | $1.75/$14 | 2m06s
As printed
84.39%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 34 of 105 (GPT 5.2), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-5.2-2025-12-11"].
Setting
model ID openai/gpt-5.2-2025-12-11; max_output_tokens=30000; reasoning_effort=xhigh
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
34GPT-5.6 LunaOpenAI · gpt-5.6-luna84.39Board publisherSep 2026[1]
33 | GPT-5.6 Luna | 84.39%±2.58 | $0.2/$1.2 | 116.89s
As printed
84.39%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 33 of 105 (GPT-5.6 Luna), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-5.6-luna"].
Setting
model ID openai/gpt-5.6-luna; max_output_tokens=30000; reasoning_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
36Inkling SmallThinking Machines · inkling-small84.11Board publisherSep 2026[1]
35 | Inkling Small | 84.11%±1.87 | $0.3/$1.2 | 3m50s
As printed
84.11%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 35 of 105 (Inkling Small), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["thinkingmachines/inkling-small"].
Setting
model ID thinkingmachines/inkling-small; temperature=1; top_p=1; max_output_tokens=30000; reasoning_effort=0.99
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
37Claude Sonnet 4.5 (Thinking)Anthropic · claude-sonnet-4-5-20250929-thinking84.10Board publisherSep 2026[1]
36 | Claude Sonnet 4.5 (Thinking) | 84.10%±1.87 | $3/$15 | 67.92s
As printed
84.10%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 36 of 105 (Claude Sonnet 4.5 (Thinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-sonnet-4-5-20250929-thinking"].
Setting
model ID anthropic/claude-sonnet-4-5-20250929-thinking; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
38Gemini 3.7 FlashGoogle · gemini-3.7-flash83.94Board publisherSep 2026[1]
37 | Gemini 3.7 Flash | 83.94%±2.00 | $1.5/$7.5 | 16.82s
As printed
83.94%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 37 of 105 (Gemini 3.7 Flash), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-3.7-flash"].
Setting
model ID google/gemini-3.7-flash; temperature=1; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
39Qwen 3.8 27BAlibaba · qwen3.8-27b83.85Board publisherSep 2026[1]
38 | Qwen 3.8 27B | 83.85%±1.98 | $0.5/$3 | 89.70s
As printed
83.85%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 38 of 105 (Qwen 3.8 27B), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["alibaba/qwen3.8-27b"].
Setting
model ID alibaba/qwen3.8-27b; temperature=1; top_p=0.95; max_output_tokens=30000; reasoning_effort=xhigh
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
40MiMo V2.5 ProXiaomi · mimo-v2.5-pro83.73Board publisherSep 2026[1]
39 | MiMo V2.5 Pro | 83.73%±2.06 | $0.435/$0.87 | 90.71s
As printed
83.73%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 39 of 105 (MiMo V2.5 Pro), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["xiaomi/mimo-v2.5-pro"].
Setting
model ID xiaomi/mimo-v2.5-pro; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
41GPT-6 LunaOpenAI · gpt-6-luna83.71Board publisherSep 2026[1]
40 | GPT-6 Luna | 83.71%±1.95 | $0.1/$0.5 | 2m50s
As printed
83.71%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 40 of 105 (GPT-6 Luna), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-6-luna"].
Setting
model ID openai/gpt-6-luna; max_output_tokens=128000; reasoning_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
42GPT 5OpenAI · gpt-5-2025-08-0783.65Board publisherSep 2026[1]
41 | GPT 5 | 83.65%±1.94 | $1.25/$10 | 3m05s
As printed
83.65%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 41 of 105 (GPT 5), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-5-2025-08-07"].
Setting
model ID openai/gpt-5-2025-08-07; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
43Hy4 PreviewTencent · hy4-preview83.60Board publisherSep 2026[1]
42 | Hy4 Preview | 83.60%±2.06 | $0.834/$2.501 | 5m50s
As printed
83.60%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 42 of 105 (Hy4 Preview), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["tencent/hy4-preview"].
Setting
model ID tencent/hy4-preview; temperature=1; top_p=1; max_output_tokens=64000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
44GLM 5.2Zhipu · glm-5.283.53Board publisherSep 2026[1]
43 | GLM 5.2 | 83.53%±2.00 | $1.4/$4.4 | 2m18s
As printed
83.53%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 43 of 105 (GLM 5.2), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["zai/glm-5.2"].
Setting
model ID zai/glm-5.2; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
45Claude Opus 4.5 (Nonthinking)Anthropic · claude-opus-4-5-2025110183.25Board publisherSep 2026[1]
44 | Claude Opus 4.5 (Nonthinking) | 83.25%±1.93 | $5/$25 | 43.30s
As printed
83.25%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 44 of 105 (Claude Opus 4.5 (Nonthinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-opus-4-5-20251101"].
Setting
model ID anthropic/claude-opus-4-5-20251101; temperature=1; max_output_tokens=30000; compute_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
46Gemini 2.5 Flash (7/17) (Thinking)Google · gemini-2.5-flash-thinking82.98Board publisherSep 2026[1]
45 | Gemini 2.5 Flash (7/17) (Thinking) | 82.98%±1.91 | $0.3/$2.5 | 22.53s
As printed
82.98%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 45 of 105 (Gemini 2.5 Flash (7/17) (Thinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-2.5-flash-thinking"].
Setting
model ID google/gemini-2.5-flash-thinking; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
47Claude Opus 4.7Anthropic · claude-opus-4-782.95Board publisherSep 2026[1]
46 | Claude Opus 4.7 | 82.95%±1.98 | $5/$25 | 67.50s
As printed
82.95%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 46 of 105 (Claude Opus 4.7), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-opus-4-7"].
Setting
model ID anthropic/claude-opus-4-7; temperature=1; max_output_tokens=30000; compute_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
48Gemini 2.5 Flash (7/17) (Nonthinking)Google · gemini-2.5-flash82.87Board publisherSep 2026[1]
47 | Gemini 2.5 Flash (7/17) (Nonthinking) | 82.87%±1.91 | $0.3/$2.5 | 22.79s
As printed
82.87%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 47 of 105 (Gemini 2.5 Flash (7/17) (Nonthinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-2.5-flash"].
Setting
model ID google/gemini-2.5-flash; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
48GPT-5.6 TerraOpenAI · gpt-5.6-terra82.87Board publisherSep 2026[1]
48 | GPT-5.6 Terra | 82.87%±1.95 | $2/$12 | 35.53s
As printed
82.87%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 48 of 105 (GPT-5.6 Terra), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-5.6-terra"].
Setting
model ID openai/gpt-5.6-terra; max_output_tokens=30000; reasoning_effort=xhigh
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
50GPT-6 SolOpenAI · gpt-6-sol82.03Board publisherSep 2026[1]
49 | GPT-6 Sol | 82.03%±1.94 | $2/$10 | 81.14s
As printed
82.03%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 49 of 105 (GPT-6 Sol), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-6-sol"].
Setting
model ID openai/gpt-6-sol; max_output_tokens=128000; reasoning_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
51Grok 4 Fast (Reasoning)SpaceX AI · grok-4-fast-reasoning81.63Board publisherSep 2026[1]
50 | Grok 4 Fast (Reasoning) | 81.63%±2.14 | $0.2/$0.5 | 12.42s
As printed
81.63%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 50 of 105 (Grok 4 Fast (Reasoning)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["grok/grok-4-fast-reasoning"].
Setting
model ID grok/grok-4-fast-reasoning; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
52Ling 3.0 FlashAnt Group · ling-3.0-flash-260780.90Board publisherSep 2026[1]
51 | Ling 3.0 Flash | 80.90%±2.04 | $0.075/$0.22 | 12.12s
As printed
80.90%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 51 of 105 (Ling 3.0 Flash), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["ant/ling-3.0-flash-2607"].
Setting
model ID ant/ling-3.0-flash-2607; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
53MiniMax-M2.1MiniMax · MiniMax-M2.180.78Board publisherSep 2026[1]
52 | MiniMax-M2.1 | 80.78%±1.83 | $0.3/$1.2 | 53.16s
As printed
80.78%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 52 of 105 (MiniMax-M2.1), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["minimax/MiniMax-M2.1"].
Setting
model ID minimax/MiniMax-M2.1; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
54GPT 5 MiniOpenAI · gpt-5-mini-2025-08-0780.58Board publisherSep 2026[1]
53 | GPT 5 Mini | 80.58%±1.92 | $0.25/$2 | 4m36s
As printed
80.58%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 53 of 105 (GPT 5 Mini), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-5-mini-2025-08-07"].
Setting
model ID openai/gpt-5-mini-2025-08-07; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
55DeepSeek V4 Flash 0731DeepSeek · deepseek-v4-flash-073180.36Board publisherSep 2026[1]
54 | DeepSeek V4 Flash 0731 | 80.36%±1.97 | $0.44/$1.32 | 77.55s
As printed
80.36%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 54 of 105 (DeepSeek V4 Flash 0731), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["deepseek/deepseek-v4-flash-0731"].
Setting
model ID deepseek/deepseek-v4-flash-0731; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
56DeepSeek V4 Pro 0813DeepSeek · deepseek-v4-pro-081380.17Board publisherSep 2026[1]
55 | DeepSeek V4 Pro 0813 | 80.17%±2.00 | $1.32/$3.96 | 2m36s
As printed
80.17%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 55 of 105 (DeepSeek V4 Pro 0813), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["deepseek/deepseek-v4-pro-0813"].
Setting
model ID deepseek/deepseek-v4-pro-0813; max_output_tokens=30000; reasoning_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
57MiniMax-M2.7MiniMax · MiniMax-M2.779.87Board publisherSep 2026[1]
56 | MiniMax-M2.7 | 79.87%±1.86 | $0.3/$1.2 | 27.25s
As printed
79.87%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 56 of 105 (MiniMax-M2.7), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["minimax/MiniMax-M2.7"].
Setting
model ID minimax/MiniMax-M2.7; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
58Grok 4 Fast (Non-Reasoning)SpaceX AI · grok-4-fast-non-reasoning79.72Board publisherSep 2026[1]
57 | Grok 4 Fast (Non-Reasoning) | 79.72%±1.87 | $0.2/$0.5 | 8.48s
As printed
79.72%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 57 of 105 (Grok 4 Fast (Non-Reasoning)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["grok/grok-4-fast-non-reasoning"].
Setting
model ID grok/grok-4-fast-non-reasoning; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
59Gemini 3.6 FlashGoogle · gemini-3.6-flash79.66Board publisherSep 2026[1]
58 | Gemini 3.6 Flash | 79.66%±1.86 | $1.5/$7.5 | 33.55s
As printed
79.66%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 58 of 105 (Gemini 3.6 Flash), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-3.6-flash"].
Setting
model ID google/gemini-3.6-flash; temperature=1; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
60Qwen 3.7 MaxAlibaba · qwen3.7-max79.40Board publisherSep 2026[1]
59 | Qwen 3.7 Max | 79.40%±1.91 | $2.5/$7.5 | 108.05s
As printed
79.40%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 59 of 105 (Qwen 3.7 Max), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["alibaba/qwen3.7-max"].
Setting
model ID alibaba/qwen3.7-max; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
61Grok 4.1 Fast (Reasoning)SpaceX AI · grok-4-1-fast-reasoning78.73Board publisherSep 2026[1]
60 | Grok 4.1 Fast (Reasoning) | 78.73%±1.87 | $0.2/$0.5 | 39.29s
As printed
78.73%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 60 of 105 (Grok 4.1 Fast (Reasoning)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["grok/grok-4-1-fast-reasoning"].
Setting
model ID grok/grok-4-1-fast-reasoning; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
62Gemini 2.5 Flash Preview (9/25) (Thinking)Google · gemini-2.5-flash-preview-09-2025-thinking78.50Board publisherSep 2026[1]
61 | Gemini 2.5 Flash Preview (9/25) (Thinking) | 78.50%±1.99 | $0.3/$2.5 | 31.39s
As printed
78.50%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 61 of 105 (Gemini 2.5 Flash Preview (9/25) (Thinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-2.5-flash-preview-09-2025-thinking"].
Setting
model ID google/gemini-2.5-flash-preview-09-2025-thinking; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
63Grok 4SpaceX AI · grok-4-070978.15Board publisherSep 2026[1]
62 | Grok 4 | 78.15%±2.08 | $3/$15 | 74.05s
As printed
78.15%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 62 of 105 (Grok 4), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["grok/grok-4-0709"].
Setting
model ID grok/grok-4-0709; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
63Kimi K2.6Moonshot AI · kimi-k2.678.15Board publisherSep 2026[1]
63 | Kimi K2.6 | 78.15%±1.79 | $0.95/$4 | 8m14s
As printed
78.15%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 63 of 105 (Kimi K2.6), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["kimi/kimi-k2.6"].
Setting
model ID kimi/kimi-k2.6; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
65Gemini 2.5 Flash Preview (9/25) (Nonthinking)Google · gemini-2.5-flash-preview-09-202577.95Board publisherSep 2026[1]
64 | Gemini 2.5 Flash Preview (9/25) (Nonthinking) | 77.95%±1.92 | $0.3/$2.5 | 22.89s
As printed
77.95%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 64 of 105 (Gemini 2.5 Flash Preview (9/25) (Nonthinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-2.5-flash-preview-09-2025"].
Setting
model ID google/gemini-2.5-flash-preview-09-2025; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
66GPT 5.4 (xhigh)OpenAI · gpt-5.4-2026-03-0577.55Board publisherSep 2026[1]
65 | GPT 5.4 (xhigh) | 77.55%±3.32 | $2.5/$15 | 4m43s
As printed
77.55%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 65 of 105 (GPT 5.4 (xhigh)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-5.4-2026-03-05"].
Setting
model ID openai/gpt-5.4-2026-03-05; max_output_tokens=30000; reasoning_effort=xhigh
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
67Grok 4.1 Fast Non-ReasoningSpaceX AI · grok-4-1-fast-non-reasoning77.46Board publisherSep 2026[1]
66 | Grok 4.1 Fast Non-Reasoning | 77.46%±2.04 | $0.2/$0.5 | 19.86s
As printed
77.46%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 66 of 105 (Grok 4.1 Fast Non-Reasoning), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["grok/grok-4-1-fast-non-reasoning"].
Setting
model ID grok/grok-4-1-fast-non-reasoning; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
68Qwen 3 VL PlusAlibaba · qwen3-vl-plus-2025-09-2377.13Board publisherSep 2026[1]
67 | Qwen 3 VL Plus | 77.13%±1.92 | $0.2/$1.6 | 71.35s
As printed
77.13%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 67 of 105 (Qwen 3 VL Plus), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["alibaba/qwen3-vl-plus-2025-09-23"].
Setting
model ID alibaba/qwen3-vl-plus-2025-09-23; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
69GPT 5.4 NanoOpenAI · gpt-5.4-nano-2026-03-1777.09Board publisherSep 2026[1]
68 | GPT 5.4 Nano | 77.09%±1.89 | $0.2/$1.25 | 20.53s
As printed
77.09%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 68 of 105 (GPT 5.4 Nano), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-5.4-nano-2026-03-17"].
Setting
model ID openai/gpt-5.4-nano-2026-03-17; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
70Qwen 3.6 PlusAlibaba · qwen3.6-plus76.96Board publisherSep 2026[1]
69 | Qwen 3.6 Plus | 76.96%±1.92 | $0.5/$3 | 2m54s
As printed
76.96%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 69 of 105 (Qwen 3.6 Plus), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["alibaba/qwen3.6-plus"].
Setting
model ID alibaba/qwen3.6-plus; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
71o3OpenAI · o3-2025-04-1676.65Board publisherSep 2026[1]
70 | o3 | 76.65%±1.87 | $2/$8 | 46.39s
As printed
76.65%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 70 of 105 (o3), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/o3-2025-04-16"].
Setting
model ID openai/o3-2025-04-16; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
72Gemini 3.5 FlashGoogle · gemini-3.5-flash76.57Board publisherSep 2026[1]
71 | Gemini 3.5 Flash | 76.57%±1.92 | $1.5/$9 | 57.08s
As printed
76.57%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 71 of 105 (Gemini 3.5 Flash), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-3.5-flash"].
Setting
model ID google/gemini-3.5-flash; temperature=1; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
73Kimi K2.5Moonshot AI · kimi-k2.5-thinking76.44Board publisherSep 2026[1]
72 | Kimi K2.5 | 76.44%±1.99 | $0.6/$3 | 2m27s
As printed
76.44%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 72 of 105 (Kimi K2.5), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["kimi/kimi-k2.5-thinking"].
Setting
model ID kimi/kimi-k2.5-thinking; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
74Gemini 3.1 Pro Preview (02/26)Google · gemini-3.1-pro-preview76.11Board publisherSep 2026[1]
73 | Gemini 3.1 Pro Preview (02/26) | 76.11%±1.92 | $2/$12 | 69.14s
As printed
76.11%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 73 of 105 (Gemini 3.1 Pro Preview (02/26)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-3.1-pro-preview"].
Setting
model ID google/gemini-3.1-pro-preview; temperature=1; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
75Claude Sonnet 5Anthropic · claude-sonnet-576.05Board publisherSep 2026[1]
74 | Claude Sonnet 5 | 76.05%±3.05 | $2/$10 | 4m12s
As printed
76.05%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 74 of 105 (Claude Sonnet 5), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-sonnet-5"].
Setting
model ID anthropic/claude-sonnet-5; temperature=1; max_output_tokens=30000; compute_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
76Gemini 2.5 Flash Lite (9/25) (Nonthinking)Google · gemini-2.5-flash-lite-preview-09-202575.82Board publisherSep 2026[1]
75 | Gemini 2.5 Flash Lite (9/25) (Nonthinking) | 75.82%±1.85 | $0.1/$0.4 | 4.49s
As printed
75.82%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 75 of 105 (Gemini 2.5 Flash Lite (9/25) (Nonthinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-2.5-flash-lite-preview-09-2025"].
Setting
model ID google/gemini-2.5-flash-lite-preview-09-2025; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
77Ling 3.0 Flash FinAnt Group · ling-3.0-flash-af-rc375.59Board publisherSep 2026[1]
76 | Ling 3.0 Flash Fin | 75.59%±2.03 | $0.06/$0.18 | 44.81s
As printed
75.59%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 76 of 105 (Ling 3.0 Flash Fin), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["ant/ling-3.0-flash-af-rc3"].
Setting
model ID ant/ling-3.0-flash-af-rc3; temperature=1; top_p=0.95; max_output_tokens=131072
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
78DeepSeek V4DeepSeek · deepseek-v4-pro75.14Board publisherSep 2026[1]
77 | DeepSeek V4 | 75.14%±2.00 | $1.32/$3.96 | 5m46s
As printed
75.14%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 77 of 105 (DeepSeek V4), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["deepseek/deepseek-v4-pro"].
Setting
model ID deepseek/deepseek-v4-pro; max_output_tokens=128000; reasoning_effort=max
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
79Grok 4.3SpaceX AI · grok-4.374.40Board publisherSep 2026[1]
78 | Grok 4.3 | 74.40%±2.02 | $1.25/$2.5 | 100.46s
As printed
74.40%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 78 of 105 (Grok 4.3), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["grok/grok-4.3"].
Setting
model ID grok/grok-4.3; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
80Claude Opus 4.1 (Thinking)Anthropic · claude-opus-4-1-20250805-thinking73.90Board publisherSep 2026[1]
79 | Claude Opus 4.1 (Thinking) | 73.90%±1.97 | $15/$75 | 57.40s
As printed
73.90%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 79 of 105 (Claude Opus 4.1 (Thinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-opus-4-1-20250805-thinking"].
Setting
model ID anthropic/claude-opus-4-1-20250805-thinking; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
81Gemini 2.5 ProGoogle · gemini-2.5-pro73.55Board publisherSep 2026[1]
80 | Gemini 2.5 Pro | 73.55%±1.91 | $1.25/$10 | 35.91s
As printed
73.55%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 80 of 105 (Gemini 2.5 Pro), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-2.5-pro"].
Setting
model ID google/gemini-2.5-pro; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
82GPT 5 NanoOpenAI · gpt-5-nano-2025-08-0772.86Board publisherSep 2026[1]
81 | GPT 5 Nano | 72.86%±1.89 | $0.05/$0.4 | 112.91s
As printed
72.86%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 81 of 105 (GPT 5 Nano), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-5-nano-2025-08-07"].
Setting
model ID openai/gpt-5-nano-2025-08-07; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
83Gemini 2.5 Flash Lite (Nonthinking)Google · gemini-2.5-flash-lite72.83Board publisherSep 2026[1]
82 | Gemini 2.5 Flash Lite (Nonthinking) | 72.83%±1.98 | $0.1/$0.4 | 4.85s
As printed
72.83%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 82 of 105 (Gemini 2.5 Flash Lite (Nonthinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-2.5-flash-lite"].
Setting
model ID google/gemini-2.5-flash-lite; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
84Qwen 3 Max ThinkingAlibaba · qwen3-max-2026-01-2372.71Board publisherSep 2026[1]
83 | Qwen 3 Max Thinking | 72.71%±1.91 | $1.2/$6 | 6m02s
As printed
72.71%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 83 of 105 (Qwen 3 Max Thinking), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["alibaba/qwen3-max-2026-01-23"].
Setting
model ID alibaba/qwen3-max-2026-01-23; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
85Claude Sonnet 4 (Nonthinking)Anthropic · claude-sonnet-4-2025051472.41Board publisherSep 2026[1]
84 | Claude Sonnet 4 (Nonthinking) | 72.41%±1.93 | $3/$15 | 25.67s
As printed
72.41%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 84 of 105 (Claude Sonnet 4 (Nonthinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-sonnet-4-20250514"].
Setting
model ID anthropic/claude-sonnet-4-20250514; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
86GLM 5.1Zhipu · glm-5.172.27Board publisherSep 2026[1]
85 | GLM 5.1 | 72.27%±2.06 | $1/$3.2 | 95.70s
As printed
72.27%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 85 of 105 (GLM 5.1), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["zai/glm-5.1"].
Setting
model ID zai/glm-5.1; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
87MiMo V2.5Xiaomi · mimo-v2.572.15Board publisherSep 2026[1]
86 | MiMo V2.5 | 72.15%±1.85 | $0.14/$0.28 | 20.26s
As printed
72.15%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 86 of 105 (MiMo V2.5), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["xiaomi/mimo-v2.5"].
Setting
model ID xiaomi/mimo-v2.5; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
88Gemini 3 Pro (11/25)Google · gemini-3-pro-preview72.04Board publisherSep 2026[1]
87 | Gemini 3 Pro (11/25) | 72.04%±1.90 | $2/$12 | 43.39s
As printed
72.04%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 87 of 105 (Gemini 3 Pro (11/25)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-3-pro-preview"].
Setting
model ID google/gemini-3-pro-preview; temperature=1; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
89Claude Opus 4.1 (Nonthinking)Anthropic · claude-opus-4-1-2025080571.75Board publisherSep 2026[1]
88 | Claude Opus 4.1 (Nonthinking) | 71.75%±2.02 | $15/$75 | 38.04s
As printed
71.75%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 88 of 105 (Claude Opus 4.1 (Nonthinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-opus-4-1-20250805"].
Setting
model ID anthropic/claude-opus-4-1-20250805; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
90Gemini 3.5 Flash LiteGoogle · gemini-3.5-flash-lite70.89Board publisherSep 2026[1]
89 | Gemini 3.5 Flash Lite | 70.89%±2.03 | $0.3/$2.5 | 18.99s
As printed
70.89%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 89 of 105 (Gemini 3.5 Flash Lite), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-3.5-flash-lite"].
Setting
model ID google/gemini-3.5-flash-lite; temperature=1; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
91Qwen 3.5 FlashAlibaba · qwen3.5-flash70.62Board publisherSep 2026[1]
90 | Qwen 3.5 Flash | 70.62%±2.09 | $0.1/$0.4 | 80.41s
As printed
70.62%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 90 of 105 (Qwen 3.5 Flash), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["alibaba/qwen3.5-flash"].
Setting
model ID alibaba/qwen3.5-flash; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
92Gemini 3 Flash (12/25)Google · gemini-3-flash-preview69.92Board publisherSep 2026[1]
91 | Gemini 3 Flash (12/25) | 69.92%±1.90 | $0.5/$3 | 23.49s
As printed
69.92%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 91 of 105 (Gemini 3 Flash (12/25)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-3-flash-preview"].
Setting
model ID google/gemini-3-flash-preview; temperature=1; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
93Claude Sonnet 4 (Thinking)Anthropic · claude-sonnet-4-20250514-thinking69.35Board publisherSep 2026[1]
92 | Claude Sonnet 4 (Thinking) | 69.35%±2.21 | $3/$15 | 39.57s
As printed
69.35%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 92 of 105 (Claude Sonnet 4 (Thinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-sonnet-4-20250514-thinking"].
Setting
model ID anthropic/claude-sonnet-4-20250514-thinking; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
94o4 MiniOpenAI · o4-mini-2025-04-1669.14Board publisherSep 2026[1]
93 | o4 Mini | 69.14%±1.96 | $1.1/$4.4 | 81.96s
As printed
69.14%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 93 of 105 (o4 Mini), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/o4-mini-2025-04-16"].
Setting
model ID openai/o4-mini-2025-04-16; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
95GLM 4.7Zhipu · glm-4.768.63Board publisherSep 2026[1]
94 | GLM 4.7 | 68.63%±2.12 | $0.6/$2.2 | 2m47s
As printed
68.63%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 94 of 105 (GLM 4.7), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["zai/glm-4.7"].
Setting
model ID zai/glm-4.7; temperature=1; top_p=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
96Mistral Medium 3.5Mistral · mistral-medium-3.567.73Board publisherSep 2026[1]
95 | Mistral Medium 3.5 | 67.73%±2.01 | $1.5/$7.5 | 104.05s
As printed
67.73%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 95 of 105 (Mistral Medium 3.5), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["mistralai/mistral-medium-3.5"].
Setting
model ID mistralai/mistral-medium-3.5; temperature=1; top_p=0.95; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
97Gemini 2.5 Flash Lite (9/25) (Thinking)Google · gemini-2.5-flash-lite-preview-09-2025-thinking66.88Board publisherSep 2026[1]
96 | Gemini 2.5 Flash Lite (9/25) (Thinking) | 66.88%±1.92 | $0.1/$0.4 | 11.52s
As printed
66.88%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 96 of 105 (Gemini 2.5 Flash Lite (9/25) (Thinking)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-2.5-flash-lite-preview-09-2025-thinking"].
Setting
model ID google/gemini-2.5-flash-lite-preview-09-2025-thinking; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
98Laguna M.1Poolside · laguna-m.165.91Board publisherSep 2026[1]
97 | Laguna M.1 | 65.91%±2.01 | N/A | 111.82s
As printed
65.91%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 97 of 105 (Laguna M.1), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["poolside/laguna-m.1"].
Setting
model ID poolside/laguna-m.1; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
99Gemini 3.1 Flash Lite PreviewGoogle · gemini-3.1-flash-lite-preview63.90Board publisherSep 2026[1]
98 | Gemini 3.1 Flash Lite Preview | 63.90%±1.82 | $0.25/$1.5 | 16.79s
As printed
63.90%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 98 of 105 (Gemini 3.1 Flash Lite Preview), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["google/gemini-3.1-flash-lite-preview"].
Setting
model ID google/gemini-3.1-flash-lite-preview; temperature=1; max_output_tokens=30000; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
100Grok 4.20 (Reasoning)SpaceX AI · grok-4.20-0309-reasoning63.41Board publisherSep 2026[1]
99 | Grok 4.20 (Reasoning) | 63.41%±2.10 | $2/$6 | 18.60s
As printed
63.41%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 99 of 105 (Grok 4.20 (Reasoning)), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["grok/grok-4.20-0309-reasoning"].
Setting
model ID grok/grok-4.20-0309-reasoning; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
101Laguna XS.2Poolside · laguna-xs.261.43Board publisherSep 2026[1]
100 | Laguna XS.2 | 61.43%±2.35 | N/A | 68.82s
As printed
61.43%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 100 of 105 (Laguna XS.2), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["poolside/laguna-xs.2"].
Setting
model ID poolside/laguna-xs.2; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
102Command A+Cohere · command-a-plus-05-202655.68Board publisherSep 2026[1]
101 | Command A+ | 55.68%±3.65 | N/A | 3m23s
As printed
55.68%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 101 of 105 (Command A+), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["cohere/command-a-plus-05-2026"].
Setting
model ID cohere/command-a-plus-05-2026; temperature=1; top_p=0.95; max_output_tokens=64000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
103Mercury 2.5Inception · mercury-2.555.09Board publisherSep 2026[1]
102 | Mercury 2.5 | 55.09%±2.10 | $0.2/$0.75 | 9.99s
As printed
55.09%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 102 of 105 (Mercury 2.5), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["inception/mercury-2.5"].
Setting
model ID inception/mercury-2.5; temperature=1; max_output_tokens=65536; reasoning_effort=high
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
104Llama 4 MaverickMeta · llama4-maverick-instruct-basic54.22Board publisherSep 2026[1]
103 | Llama 4 Maverick | 54.22%±1.87 | $0.22/$0.88 | 25.05s
As printed
54.22%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 103 of 105 (Llama 4 Maverick), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["fireworks/llama4-maverick-instruct-basic"].
Setting
model ID fireworks/llama4-maverick-instruct-basic; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
105Llama 4 ScoutMeta · Llama-4-Scout-17B-16E-Instruct50.59Board publisherSep 2026[1]
104 | Llama 4 Scout | 50.59%±1.90 | $0.18/$0.59 | 11.32s
As printed
50.59%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 104 of 105 (Llama 4 Scout), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["together/meta-llama/Llama-4-Scout-17B-16E-Instruct"].
Setting
model ID together/meta-llama/Llama-4-Scout-17B-16E-Instruct; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
106Nemotron 3.5 LightningNVIDIA · nemotron-lightning-3p5-30b-a3b4.27Board publisherSep 2026[1]
105 | Nemotron 3.5 Lightning | 4.27%±0.49 | $0.05/$0.2 | 105.52s
As printed
4.27%
Where
Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 105 of 105 (Nemotron 3.5 Lightning), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["fireworks/nemotron-lightning-3p5-30b-a3b"].
Setting
model ID fireworks/nemotron-lightning-3p5-30b-a3b; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedScribe leaderboard
References

2 documents support this board

  1. 1.Vals AI MedScribe leaderboardofficial leaderboard, Vals AI, 3 Sep 2026. Every result it supports
  2. 2.Vals AI: Gemini 4 Argon model pageofficial leaderboard, Vals AI, 29 Oct 2026. Every result it supports