Clinical Benchmarks

MedCode (Vals AI)

ICD-10-CM coding of whole hospital stays from discharge summaries and notes, checked against professional coders.

More about this boardLess

ICD-10-CM diagnosis coding for entire hospital stays: models assign primary and secondary codes from discharge summaries plus progress/consult notes; ground truth double-annotated by certified professional coders.

Vals AI runs every model itself; 103 models on the board, last updated September 29, 2026. Vals AI pairs this board with MedScribe, and its writeup notes that coding accuracy lags documentation quality.

Published by Vals AI (dataset with Protege), released Feb 2026. 2,755 patient records. Percentage accuracy 0-100, higher better.

Rows on the board
103
Board last updated
29 Sep 2026
Publisher
Vals AI (dataset with Protege)
Rows
104
Models
95 of 103 on the board
Released
Feb 2026
Measured to
Oct 2026
Unit
2,755 patient records
Documents cited
1

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

104 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

104 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 5Anthropic63.57Board publisherSep 2026[1]
1 | Claude Opus 5 | 63.57%±1.99 | $5/$25 | 24.50s
As printed
63.57%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 1 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-opus-5"].
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
2Gemini 3.1 Pro Preview (02/26)Google59.06Board publisherSep 2026[1]
2 | Gemini 3.1 Pro Preview (02/26) | 59.06%±2.00 | $2/$12 | 38.52s
As printed
59.06%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 2 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["google/gemini-3.1-pro-preview"].
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
3Gemini 4 ArgonGoogle58.80Board publisherOct 2026[1]
3 | Gemini 4 Argon | 58.80% | $4 / $20 | 16.11k | 79.53s
As printed
58.80%
Where
MedCode leaderboard, Overall task, rank 3 of 104; Accuracy column; board dated Oct 29, 2026. Rendered table row (Apify crawl 2026-10-31); the page summary repeats it: "Gemini 4 Argon (58.80%)".
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
4Claude Fable 5Anthropic56.07Board publisherSep 2026[1]
3 | Claude Fable 5 | 56.07%±2.20 | $10/$50 | 91.44s
As printed
56.07%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 3 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-fable-5"].
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
5Gemini 3 Flash (12/25)Google55.92Board publisherSep 2026[1]
4 | Gemini 3 Flash (12/25) | 55.92%±2.11 | $0.5/$3 | 44.15s
As printed
55.92%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 4 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["google/gemini-3-flash-preview"].
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
6Gemini 3.5 FlashGoogle55.83Board publisherSep 2026[1]
5 | Gemini 3.5 Flash | 55.83%±2.11 | $1.5/$9 | 25.29s
As printed
55.83%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 5 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["google/gemini-3.5-flash"].
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
7Claude Opus 4.7Anthropic54.86Board publisherSep 2026[1]
6 | Claude Opus 4.7 | 54.86%±2.21 | $5/$25 | 54.25s
As printed
54.86%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 6 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-opus-4-7"].
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
8Claude Fable 5.1Anthropic53.51Board publisherSep 2026[1]
7 | Claude Fable 5.1 | 53.51%±2.17 | $10/$50 | 3m35s
As printed
53.51%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 7 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-fable-5-1"].
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
9Gemini 3.7 FlashGoogle · gemini-3.7-flash53.39Board publisherSep 2026[1]
8 | Gemini 3.7 Flash | 53.39%±2.12 | $1.5/$7.5 | 9.16s
As printed
53.39%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 8 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["google/gemini-3.7-flash"].
Setting
model ID google/gemini-3.7-flash; reasoning_effort=high; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
10Claude Opus 4.8Anthropic53.22Board publisherSep 2026[1]
9 | Claude Opus 4.8 | 53.22%±2.17 | $5/$25 | 105.92s
As printed
53.22%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 9 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-opus-4-8"].
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
11Gemini 3.6 FlashGoogle53.15Board publisherSep 2026[1]
10 | Gemini 3.6 Flash | 53.15%±2.16 | $1.5/$7.5 | 16.68s
As printed
53.15%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 10 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["google/gemini-3.6-flash"].
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
12Claude Sonnet 5.5Anthropic · claude-sonnet-5-552.92Board publisherSep 2026[1]
11 | Claude Sonnet 5.5 | 52.92%±2.12 | $2/$10 | 3m59s
As printed
52.92%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 11 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-sonnet-5-5"].
Setting
model ID anthropic/claude-sonnet-5-5; compute_effort=max; temperature=1; max_output_tokens=128000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
13GPT 5.1OpenAI52.73Board publisherSep 2026[1]
12 | GPT 5.1 | 52.73%±2.15 | $1.25/$10 | 54.55s
As printed
52.73%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 12 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-5.1-2025-11-13"].
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
14Gemini 3 Pro (11/25)Google · gemini-3-pro-preview52.20Board publisherSep 2026[1]
13 | Gemini 3 Pro (11/25) | 52.20%±2.07 | $2/$12 | 55.84s
As printed
52.20%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 13 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["google/gemini-3-pro-preview"].
Setting
model ID google/gemini-3-pro-preview; reasoning_effort=high; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
15Muse SparkMeta · muse_spark51.31Board publisherSep 2026[1]
14 | Muse Spark | 51.31%±2.24 | N/A | 2m03s
As printed
51.31%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 14 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
16Gemini 2.5 ProGoogle · gemini-2.5-pro50.59Board publisherSep 2026[1]
15 | Gemini 2.5 Pro | 50.59%±2.11 | $1.25/$10 | 27.41s
As printed
50.59%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 15 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
17Claude Opus 5.5Anthropic · claude-opus-5-549.80Board publisherSep 2026[1]
16 | Claude Opus 5.5 | 49.80%±2.27 | $4/$20 | 4m07s
As printed
49.80%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 16 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-opus-5-5"].
Setting
model ID anthropic/claude-opus-5-5; compute_effort=max; temperature=1; max_output_tokens=128000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
18GPT 5.2OpenAI · gpt-5.2-2025-12-1149.75Board publisherSep 2026[1]
17 | GPT 5.2 | 49.75%±2.26 | $1.75/$14 | 2m37s
As printed
49.75%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 17 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-5.2-2025-12-11"].
Setting
model ID openai/gpt-5.2-2025-12-11; reasoning_effort=xhigh; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
19GPT 5OpenAI · gpt-5-2025-08-0749.63Board publisherSep 2026[1]
18 | GPT 5 | 49.63%±2.10 | $1.25/$10 | 58.27s
As printed
49.63%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 18 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-5-2025-08-07"].
Setting
model ID openai/gpt-5-2025-08-07; reasoning_effort=high; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
20Grok 4.7SpaceX AI · grok-4.749.55Board publisherSep 2026[1]
19 | Grok 4.7 | 49.55%±2.17 | $2/$6 | 3m33s
As printed
49.55%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 19 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["grok/grok-4.7"].
Setting
model ID grok/grok-4.7; reasoning_effort=xhigh; temperature=1; top_p=0.95
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
21Muse Spark 1.2Meta · muse_spark_1_249.35Board publisherSep 2026[1]
20 | Muse Spark 1.2 | 49.35%±2.19 | $1.25/$4.25 | 60.17s
As printed
49.35%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 20 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["meta/muse_spark_1_2"].
Setting
model ID meta/muse_spark_1_2; reasoning_effort=xhigh; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
22Claude Opus 4.5 (Thinking)Anthropic · claude-opus-4-5-20251101-thinking49.16Board publisherSep 2026[1]
21 | Claude Opus 4.5 (Thinking) | 49.16%±2.01 | $5/$25 | 60.84s
As printed
49.16%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 21 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-opus-4-5-20251101-thinking"].
Setting
model ID anthropic/claude-opus-4-5-20251101-thinking; compute_effort=high; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
23Claude Opus 4.6 (Thinking)Anthropic · claude-opus-4-6-thinking49.13Board publisherSep 2026[1]
22 | Claude Opus 4.6 (Thinking) | 49.13%±2.08 | $5/$25 | 2m36s
As printed
49.13%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 22 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-opus-4-6-thinking"].
Setting
model ID anthropic/claude-opus-4-6-thinking; compute_effort=max; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
24GPT 5.5OpenAI · gpt-5.549.10Board publisherSep 2026[1]
23 | GPT 5.5 | 49.10%±2.19 | $5/$30 | 2m40s
As printed
49.10%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 23 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-5.5"].
Setting
model ID openai/gpt-5.5; reasoning_effort=xhigh; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
25Kimi K3Moonshot AI · kimi-k348.88Board publisherSep 2026[1]
24 | Kimi K3 | 48.88%±2.19 | $3/$15 | 116.18s
As printed
48.88%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 24 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["kimi/kimi-k3"].
Setting
model ID kimi/kimi-k3; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
26GPT-6.1 SolOpenAI · gpt-6.1-sol48.84Board publisherSep 2026[1]
25 | GPT-6.1 Sol | 48.84%±2.12 | $2/$10 | 115.34s
As printed
48.84%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 25 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-6.1-sol"].
Setting
model ID openai/gpt-6.1-sol; reasoning_effort=max; max_output_tokens=128000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
27GPT-6 AstraOpenAI48.49Board publisherSep 2026[1]
26 | GPT-6 Astra | 48.49%±2.13 | $10/$50 | 102.86s
As printed
48.49%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 26 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-6-astra"].
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
28Claude Opus 4.6 (Nonthinking)Anthropic · claude-opus-4-648.24Board publisherSep 2026[1]
27 | Claude Opus 4.6 (Nonthinking) | 48.24%±2.05 | $5/$25 | 4.06s
As printed
48.24%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 27 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-opus-4-6"].
Setting
model ID anthropic/claude-opus-4-6; compute_effort=max; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
29Gemini 3.8 FlashGoogle · gemini-3.8-flash48.13Board publisherSep 2026[1]
28 | Gemini 3.8 Flash | 48.13%±2.18 | $1.5/$7.5 | 42.89s
As printed
48.13%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 28 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["google/gemini-3.8-flash"].
Setting
model ID google/gemini-3.8-flash; reasoning_effort=high; temperature=1; max_output_tokens=65536
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
30Gemini 3.1 Flash Lite PreviewGoogle · gemini-3.1-flash-lite-preview47.60Board publisherSep 2026[1]
29 | Gemini 3.1 Flash Lite Preview | 47.60%±2.07 | $0.25/$1.5 | 8.55s
As printed
47.60%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 29 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["google/gemini-3.1-flash-lite-preview"].
Setting
model ID google/gemini-3.1-flash-lite-preview; reasoning_effort=high; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
31Claude Sonnet 5Anthropic · claude-sonnet-547.54Board publisherSep 2026[1]
30 | Claude Sonnet 5 | 47.54%±2.27 | $2/$10 | 2m15s
As printed
47.54%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 30 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-sonnet-5"].
Setting
model ID anthropic/claude-sonnet-5; compute_effort=max; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
32o3OpenAI · o3-2025-04-1647.29Board publisherSep 2026[1]
31 | o3 | 47.29%±2.16 | $2/$8 | 17.68s
As printed
47.29%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 31 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/o3-2025-04-16"].
Setting
model ID openai/o3-2025-04-16; reasoning_effort=high; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
33Claude Opus 4.1 (Thinking)Anthropic · claude-opus-4-1-20250805-thinking47.23Board publisherSep 2026[1]
32 | Claude Opus 4.1 (Thinking) | 47.23%±2.07 | $15/$75 | 33.26s
As printed
47.23%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 32 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
34GPT-6 SolOpenAI · gpt-6-sol47.07Board publisherSep 2026[1]
33 | GPT-6 Sol | 47.07%±2.12 | $2/$10 | 62.71s
As printed
47.07%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 33 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-6-sol"].
Setting
model ID openai/gpt-6-sol; reasoning_effort=max; max_output_tokens=128000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
35MiniMax-M3MiniMax · MiniMax-M346.29Board publisherSep 2026[1]
34 | MiniMax-M3 | 46.29%±2.10 | $0.6/$2.4 | 63.12s
As printed
46.29%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 34 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["minimax/MiniMax-M3"].
Setting
model ID minimax/MiniMax-M3; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
36Claude Opus 4.5 (Nonthinking)Anthropic · claude-opus-4-5-2025110145.17Board publisherSep 2026[1]
35 | Claude Opus 4.5 (Nonthinking) | 45.17%±1.89 | $5/$25 | 5.02s
As printed
45.17%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 35 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-opus-4-5-20251101"].
Setting
model ID anthropic/claude-opus-4-5-20251101; compute_effort=high; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
37MiMo V2.6 ProXiaomi · mimo-v2.6-pro44.97Board publisherSep 2026[1]
36 | MiMo V2.6 Pro | 44.97%±2.10 | $0.435/$0.87 | 2m57s
As printed
44.97%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 36 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
38Grok 4.6SpaceX AI · grok-4.644.71Board publisherSep 2026[1]
37 | Grok 4.6 | 44.71%±2.26 | $2/$6 | 2m07s
As printed
44.71%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 37 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["grok/grok-4.6"].
Setting
model ID grok/grok-4.6; reasoning_effort=high; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
39GPT-6 LunaOpenAI · gpt-6-luna44.69Board publisherSep 2026[1]
38 | GPT-6 Luna | 44.69%±2.30 | $0.1/$0.5 | 108.77s
As printed
44.69%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 38 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-6-luna"].
Setting
model ID openai/gpt-6-luna; reasoning_effort=max; max_output_tokens=128000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
40Claude Sonnet 4.5 (Thinking)Anthropic · claude-sonnet-4-5-20250929-thinking44.13Board publisherSep 2026[1]
39 | Claude Sonnet 4.5 (Thinking) | 44.13%±2.00 | $3/$15 | 74.33s
As printed
44.13%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 39 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
41GPT-5.6 SolOpenAI · gpt-5.6-sol43.97Board publisherSep 2026[1]
40 | GPT-5.6 Sol | 43.97%±2.26 | $4/$20 | 96.59s
As printed
43.97%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 40 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-5.6-sol"].
Setting
model ID openai/gpt-5.6-sol; reasoning_effort=max; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
42Gemini 3.5 Flash LiteGoogle · gemini-3.5-flash-lite43.49Board publisherSep 2026[1]
41 | Gemini 3.5 Flash Lite | 43.49%±1.95 | $0.3/$2.5 | 6.02s
As printed
43.49%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 41 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["google/gemini-3.5-flash-lite"].
Setting
model ID google/gemini-3.5-flash-lite; reasoning_effort=high; temperature=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
43GPT-5.6 TerraOpenAI · gpt-5.6-terra43.41Board publisherSep 2026[1]
42 | GPT-5.6 Terra | 43.41%±2.17 | $2/$12 | 18.41s
As printed
43.41%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 42 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-5.6-terra"].
Setting
model ID openai/gpt-5.6-terra; reasoning_effort=xhigh; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
44Grok 4.5SpaceX AI · grok-4.543.29Board publisherSep 2026[1]
43 | Grok 4.5 | 43.29%±2.31 | $2/$6 | 59.64s
As printed
43.29%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 43 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["grok/grok-4.5"].
Setting
model ID grok/grok-4.5; reasoning_effort=high; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
45Hy4 PreviewTencent · hy4-preview43.25Board publisherSep 2026[1]
44 | Hy4 Preview | 43.25%±2.13 | $0.834/$2.501 | 6m39s
As printed
43.25%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 44 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
46GPT 5 MiniOpenAI · gpt-5-mini-2025-08-0743.05Board publisherSep 2026[1]
45 | GPT 5 Mini | 43.05%±2.04 | $0.25/$2 | 28.17s
As printed
43.05%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 45 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-5-mini-2025-08-07"].
Setting
model ID openai/gpt-5-mini-2025-08-07; reasoning_effort=high; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
47GLM 5.3Zhipu · glm-5.342.86Board publisherSep 2026[1]
46 | GLM 5.3 | 42.86%±2.11 | $1.4/$4.4 | 2m49s
As printed
42.86%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 46 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["zai/glm-5.3"].
Setting
model ID zai/glm-5.3; reasoning_effort=max; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
48DeepSeek V4 Pro 0813DeepSeek · deepseek-v4-pro-081342.47Board publisherSep 2026[1]
47 | DeepSeek V4 Pro 0813 | 42.47%±2.16 | $1.32/$3.96 | 3m01s
As printed
42.47%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 47 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["deepseek/deepseek-v4-pro-0813"].
Setting
model ID deepseek/deepseek-v4-pro-0813; reasoning_effort=max; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
49GPT-5.6 LunaOpenAI · gpt-5.6-luna42.39Board publisherSep 2026[1]
48 | GPT-5.6 Luna | 42.39%±2.27 | $0.2/$1.2 | 81.28s
As printed
42.39%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 48 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-5.6-luna"].
Setting
model ID openai/gpt-5.6-luna; reasoning_effort=max; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
50GLM 5.1Zhipu · glm-5.141.60Board publisherSep 2026[1]
49 | GLM 5.1 | 41.60%±2.12 | $1/$3.2 | 77.58s
As printed
41.60%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 49 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
51DeepSeek V4 Flash 0731DeepSeek · deepseek-v4-flash-073141.41Board publisherSep 2026[1]
50 | DeepSeek V4 Flash 0731 | 41.41%±2.15 | $0.44/$1.32 | 2m07s
As printed
41.41%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 50 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["deepseek/deepseek-v4-flash-0731"].
Setting
model ID deepseek/deepseek-v4-flash-0731; reasoning_effort=high; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
52Claude Opus 4.1 (Nonthinking)Anthropic · claude-opus-4-1-2025080541.37Board publisherSep 2026[1]
51 | Claude Opus 4.1 (Nonthinking) | 41.37%±1.96 | $15/$75 | 13.08s
As printed
41.37%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 51 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
53GPT 5.4 (xhigh)OpenAI · gpt-5.4-2026-03-0541.29Board publisherSep 2026[1]
52 | GPT 5.4 (xhigh) | 41.29%±2.15 | $2.5/$15 | 3m07s
As printed
41.29%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 52 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-5.4-2026-03-05"].
Setting
model ID openai/gpt-5.4-2026-03-05; reasoning_effort=xhigh; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
54InklingThinking Machines · inkling41.19Board publisherSep 2026[1]
53 | Inkling | 41.19%±2.23 | $1/$4.05 | 2m47s
As printed
41.19%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 53 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["thinkingmachines/inkling"].
Setting
model ID thinkingmachines/inkling; reasoning_effort=0.99; temperature=1; top_p=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
55DeepSeek V4.1 FlashDeepSeek · deepseek-v4.1-flash41.17Board publisherSep 2026[1]
54 | DeepSeek V4.1 Flash | 41.17%±2.04 | $0.3/$1.2 | 35.13s
As printed
41.17%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 54 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["deepseek/deepseek-v4.1-flash"].
Setting
model ID deepseek/deepseek-v4.1-flash; reasoning_effort=high; max_output_tokens=384000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
56MiMo V2.6 FlashXiaomi · mimo-v2.6-flash41.06Board publisherSep 2026[1]
55 | MiMo V2.6 Flash | 41.06%±2.03 | $0.14/$0.28 | 93.37s
As printed
41.06%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 55 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
57GPT 5.4 NanoOpenAI · gpt-5.4-nano-2026-03-1741.03Board publisherSep 2026[1]
56 | GPT 5.4 Nano | 41.03%±2.26 | $0.2/$1.25 | 8.04s
As printed
41.03%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 56 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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; reasoning_effort=high; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
58GLM 5.2Zhipu · glm-5.240.77Board publisherSep 2026[1]
57 | GLM 5.2 | 40.77%±2.17 | $1.4/$4.4 | 95.27s
As printed
40.77%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 57 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
59Qwen 3.8 MaxAlibaba · qwen3.8-max40.67Board publisherSep 2026[1]
58 | Qwen 3.8 Max | 40.67%±2.03 | $2/$6 | 6m18s
As printed
40.67%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 58 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
60Claude Sonnet 4.5 (Nonthinking)Anthropic · claude-sonnet-4-5-2025092940.57Board publisherSep 2026[1]
59 | Claude Sonnet 4.5 (Nonthinking) | 40.57%±2.00 | $3/$15 | 12.01s
As printed
40.57%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 59 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
61Gemini 2.5 Flash Preview (9/25) (Nonthinking)Google · gemini-2.5-flash-preview-09-202540.54Board publisherSep 2026[1]
60 | Gemini 2.5 Flash Preview (9/25) (Nonthinking) | 40.54%±1.93 | $0.3/$2.5 | 12.70s
As printed
40.54%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 60 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
62DeepSeek V4DeepSeek · deepseek-v4-pro40.45Board publisherSep 2026[1]
61 | DeepSeek V4 | 40.45%±2.12 | $1.32/$3.96 | 6m23s
As printed
40.45%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 61 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["deepseek/deepseek-v4-pro"].
Setting
model ID deepseek/deepseek-v4-pro; reasoning_effort=max; max_output_tokens=128000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
63Gemini 2.5 Flash (7/17) (Thinking)Google · gemini-2.5-flash-thinking40.36Board publisherSep 2026[1]
62 | Gemini 2.5 Flash (7/17) (Thinking) | 40.36%±1.95 | $0.3/$2.5 | 22.83s
As printed
40.36%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 62 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
64Gemini 2.5 Flash Preview (9/25) (Thinking)Google · gemini-2.5-flash-preview-09-2025-thinking40.33Board publisherSep 2026[1]
63 | Gemini 2.5 Flash Preview (9/25) (Thinking) | 40.33%±1.92 | $0.3/$2.5 | 16.11s
As printed
40.33%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 63 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
65Kimi K2.6Moonshot AI · kimi-k2.640.14Board publisherSep 2026[1]
64 | Kimi K2.6 | 40.14%±2.04 | $0.95/$4 | 5m05s
As printed
40.14%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 64 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
66Kimi K2.5Moonshot AI · kimi-k2.5-thinking39.32Board publisherSep 2026[1]
65 | Kimi K2.5 | 39.32%±2.12 | $0.6/$3 | 75.45s
As printed
39.32%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 65 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
67Qwen 3.7 MaxAlibaba · qwen3.7-max38.75Board publisherSep 2026[1]
66 | Qwen 3.7 Max | 38.75%±2.20 | $2.5/$7.5 | 28.75s
As printed
38.75%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 66 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
68Nemotron 3 UltraNVIDIA · nemotron-3-ultra-550b-a55b38.62Board publisherSep 2026[1]
67 | Nemotron 3 Ultra | 38.62%±2.00 | N/A | 18.68s
As printed
38.62%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 67 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["nvidia/nemotron-3-ultra-550b-a55b"].
Setting
model ID nvidia/nemotron-3-ultra-550b-a55b; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
69Gemini 2.5 Flash (7/17) (Nonthinking)Google · gemini-2.5-flash38.42Board publisherSep 2026[1]
68 | Gemini 2.5 Flash (7/17) (Nonthinking) | 38.42%±1.92 | $0.3/$2.5 | 22.14s
As printed
38.42%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 68 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
70Grok 4SpaceX AI · grok-4-070938.08Board publisherSep 2026[1]
69 | Grok 4 | 38.08%±2.21 | $3/$15 | 89.00s
As printed
38.08%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 69 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
71Grok 4.3SpaceX AI · grok-4.338.07Board publisherSep 2026[1]
70 | Grok 4.3 | 38.07%±2.08 | $1.25/$2.5 | 43.92s
As printed
38.07%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 70 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
72Inkling SmallThinking Machines · inkling-small37.89Board publisherSep 2026[1]
71 | Inkling Small | 37.89%±2.21 | $0.3/$1.2 | 3m11s
As printed
37.89%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 71 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["thinkingmachines/inkling-small"].
Setting
model ID thinkingmachines/inkling-small; reasoning_effort=0.99; temperature=1; top_p=1; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
73Grok 4 Fast (Reasoning)SpaceX AI · grok-4-fast-reasoning37.38Board publisherSep 2026[1]
72 | Grok 4 Fast (Reasoning) | 37.38%±1.94 | $0.2/$0.5 | 17.52s
As printed
37.38%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 72 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
74Qwen 3.6 PlusAlibaba · qwen3.6-plus36.89Board publisherSep 2026[1]
73 | Qwen 3.6 Plus | 36.89%±2.02 | $0.5/$3 | 56.22s
As printed
36.89%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 73 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
75Llama 4 MaverickMeta · llama4-maverick-instruct-basic36.51Board publisherSep 2026[1]
74 | Llama 4 Maverick | 36.51%±1.99 | $0.22/$0.88 | 21.24s
As printed
36.51%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 74 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
76Claude Sonnet 4 (Thinking)Anthropic · claude-sonnet-4-20250514-thinking34.96Board publisherSep 2026[1]
75 | Claude Sonnet 4 (Thinking) | 34.96%±1.94 | $3/$15 | 39.80s
As printed
34.96%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 75 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
77MiniMax-M2.7MiniMax · MiniMax-M2.734.44Board publisherSep 2026[1]
76 | MiniMax-M2.7 | 34.44%±1.99 | $0.3/$1.2 | 30.25s
As printed
34.44%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 76 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
78Gemini 2.5 Flash Lite (9/25) (Thinking)Google · gemini-2.5-flash-lite-preview-09-2025-thinking34.19Board publisherSep 2026[1]
77 | Gemini 2.5 Flash Lite (9/25) (Thinking) | 34.19%±1.74 | $0.1/$0.4 | 10.49s
As printed
34.19%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 77 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
79MiniMax-M2.1MiniMax · MiniMax-M2.134.08Board publisherSep 2026[1]
78 | MiniMax-M2.1 | 34.08%±1.94 | $0.3/$1.2 | 19.55s
As printed
34.08%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 78 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
80Claude Sonnet 4 (Nonthinking)Anthropic · claude-sonnet-4-2025051433.94Board publisherSep 2026[1]
79 | Claude Sonnet 4 (Nonthinking) | 33.94%±1.91 | $3/$15 | 7.30s
As printed
33.94%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 79 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
81o4 MiniOpenAI · o4-mini-2025-04-1633.79Board publisherSep 2026[1]
80 | o4 Mini | 33.79%±2.02 | $1.1/$4.4 | 21.06s
As printed
33.79%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 80 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/o4-mini-2025-04-16"].
Setting
model ID openai/o4-mini-2025-04-16; reasoning_effort=high; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
82Mistral Medium 3.5Mistral · mistral-medium-3.533.75Board publisherSep 2026[1]
81 | Mistral Medium 3.5 | 33.75%±1.15 | $1.5/$7.5 | 34.88s
As printed
33.75%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 81 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["mistralai/mistral-medium-3.5"].
Setting
model ID mistralai/mistral-medium-3.5; reasoning_effort=high; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
83Qwen 3.5 FlashAlibaba · qwen3.5-flash33.00Board publisherSep 2026[1]
82 | Qwen 3.5 Flash | 33.00%±1.79 | $0.1/$0.4 | 63.07s
As printed
33.00%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 82 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
84GLM 4.7Zhipu · glm-4.732.77Board publisherSep 2026[1]
83 | GLM 4.7 | 32.77%±2.00 | $0.6/$2.2 | 2m03s
As printed
32.77%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 83 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
85Claude Haiku 4.5 (Thinking)Anthropic · claude-haiku-4-5-20251001-thinking32.68Board publisherSep 2026[1]
84 | Claude Haiku 4.5 (Thinking) | 32.68%±2.00 | $1/$5 | 34.29s
As printed
32.68%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 84 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
86MiMo V2.5 ProXiaomi · mimo-v2.5-pro32.48Board publisherSep 2026[1]
85 | MiMo V2.5 Pro | 32.48%±1.91 | $0.435/$0.87 | 38.45s
As printed
32.48%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 85 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
87Ling 3.0 FlashAnt Group · ling-3.0-flash-260732.27Board publisherSep 2026[1]
86 | Ling 3.0 Flash | 32.27%±1.91 | $0.075/$0.22 | 9.65s
As printed
32.27%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 86 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
88Grok 4.20 (Reasoning)SpaceX AI · grok-4.20-0309-reasoning32.16Board publisherSep 2026[1]
87 | Grok 4.20 (Reasoning) | 32.16%±2.12 | $2/$6 | 16.55s
As printed
32.16%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 87 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
89MiMo V2.5Xiaomi · mimo-v2.531.89Board publisherSep 2026[1]
88 | MiMo V2.5 | 31.89%±2.02 | $0.14/$0.28 | 17.70s
As printed
31.89%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 88 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
90Qwen 3 VL PlusAlibaba · qwen3-vl-plus-2025-09-2331.65Board publisherSep 2026[1]
89 | Qwen 3 VL Plus | 31.65%±1.84 | $0.2/$1.6 | 9.95s
As printed
31.65%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 89 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
91Qwen 3 Max ThinkingAlibaba · qwen3-max-2026-01-2331.37Board publisherSep 2026[1]
90 | Qwen 3 Max Thinking | 31.37%±1.89 | $1.2/$6 | 3m02s
As printed
31.37%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 90 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
92Mercury 2.5Inception · mercury-2.531.33Board publisherSep 2026[1]
91 | Mercury 2.5 | 31.33%±1.95 | $0.2/$0.75 | 7.93s
As printed
31.33%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 91 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["inception/mercury-2.5"].
Setting
model ID inception/mercury-2.5; reasoning_effort=high; temperature=1; max_output_tokens=65536
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
93GPT 5 NanoOpenAI · gpt-5-nano-2025-08-0730.44Board publisherSep 2026[1]
92 | GPT 5 Nano | 30.44%±1.95 | $0.05/$0.4 | 29.74s
As printed
30.44%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 92 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-5-nano-2025-08-07"].
Setting
model ID openai/gpt-5-nano-2025-08-07; reasoning_effort=high; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
94Grok 4 Fast (Non-Reasoning)SpaceX AI · grok-4-fast-non-reasoning30.04Board publisherSep 2026[1]
93 | Grok 4 Fast (Non-Reasoning) | 30.04%±1.97 | $0.2/$0.5 | 18.21s
As printed
30.04%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 93 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
95Ling 3.0 Flash FinAnt Group · ling-3.0-flash-af-rc329.30Board publisherSep 2026[1]
94 | Ling 3.0 Flash Fin | 29.30%±1.94 | $0.06/$0.18 | 31.17s
As printed
29.30%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 94 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
96Qwen 3.8 27BAlibaba · qwen3.8-27b28.70Board publisherSep 2026[1]
95 | Qwen 3.8 27B | 28.70%±1.97 | $0.5/$3 | 89.38s
As printed
28.70%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 95 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["alibaba/qwen3.8-27b"].
Setting
model ID alibaba/qwen3.8-27b; reasoning_effort=xhigh; temperature=1; top_p=0.95; max_output_tokens=30000
Reported by
official leaderboard
Document
[1] Vals AI MedCode leaderboard
97Grok 4.1 Fast Non-ReasoningSpaceX AI · grok-4-1-fast-non-reasoning28.35Board publisherSep 2026[1]
96 | Grok 4.1 Fast Non-Reasoning | 28.35%±1.92 | $0.2/$0.5 | 4.50s
As printed
28.35%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 96 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
98Grok 4.1 Fast (Reasoning)SpaceX AI · grok-4-1-fast-reasoning28.08Board publisherSep 2026[1]
97 | Grok 4.1 Fast (Reasoning) | 28.08%±1.99 | $0.2/$0.5 | 46.50s
As printed
28.08%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 97 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
99Gemini 2.5 Flash Lite (Nonthinking)Google · gemini-2.5-flash-lite27.11Board publisherSep 2026[1]
98 | Gemini 2.5 Flash Lite (Nonthinking) | 27.11%±1.84 | $0.1/$0.4 | 5.75s
As printed
27.11%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 98 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
100Gemini 2.5 Flash Lite (9/25) (Nonthinking)Google · gemini-2.5-flash-lite-preview-09-202527.08Board publisherSep 2026[1]
99 | Gemini 2.5 Flash Lite (9/25) (Nonthinking) | 27.08%±1.91 | $0.1/$0.4 | 6.24s
As printed
27.08%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 99 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
101Llama 4 ScoutMeta · Llama-4-Scout-17B-16E-Instruct23.31Board publisherSep 2026[1]
100 | Llama 4 Scout | 23.31%±1.75 | $0.18/$0.59 | 10.74s
As printed
23.31%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 100 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
102Laguna M.1Poolside · laguna-m.123.11Board publisherSep 2026[1]
101 | Laguna M.1 | 23.11%±1.69 | N/A | 71.00s
As printed
23.11%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 101 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
103Laguna XS.2Poolside · laguna-xs.221.25Board publisherSep 2026[1]
102 | Laguna XS.2 | 21.25%±1.70 | N/A | 33.09s
As printed
21.25%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 102 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
104Command A+Cohere · command-a-plus-05-202619.72Board publisherSep 2026[1]
103 | Command A+ | 19.72%±1.83 | N/A | 103.75s
As printed
19.72%
Where
MedCode leaderboard, Overall task, All Models expanded, rank 103 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded 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 MedCode leaderboard
References

1 document supports this board

  1. 1.Vals AI MedCode leaderboardofficial leaderboard, Vals AI, 29 Sep 2026. Every result it supports