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.
- Claude Opus 5
- Gemini 3.1 Pro Preview (02/26)
- Gemini 4 Argon
- Claude Fable 5
- Gemini 3 Flash (12/25)
- Gemini 3.5 Flash
- Claude Opus 4.7
- Claude Fable 5.1
- Gemini 3.7 Flash
- Claude Opus 4.8
- Gemini 3.6 Flash
- Claude Sonnet 5.5
- GPT 5.1
- Gemini 3 Pro (11/25)
- Muse Spark
- Gemini 2.5 Pro
- Claude Opus 5.5
- GPT 5.2
- GPT 5
- Grok 4.7
- Muse Spark 1.2
- Claude Opus 4.5 (Thinking)
- Claude Opus 4.6 (Thinking)
- GPT 5.5
- Kimi K3
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
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
3Gemini 4 ArgonGoogle58.80Board publisherOct 2026[1]
3 | Gemini 4 Argon | 58.80% | $4 / $20 | 16.11k | 79.53s
4Claude Fable 5Anthropic56.07Board publisherSep 2026[1]
3 | Claude Fable 5 | 56.07%±2.20 | $10/$50 | 91.44s
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
6Gemini 3.5 FlashGoogle55.83Board publisherSep 2026[1]
5 | Gemini 3.5 Flash | 55.83%±2.11 | $1.5/$9 | 25.29s
7Claude Opus 4.7Anthropic54.86Board publisherSep 2026[1]
6 | Claude Opus 4.7 | 54.86%±2.21 | $5/$25 | 54.25s
8Claude Fable 5.1Anthropic53.51Board publisherSep 2026[1]
7 | Claude Fable 5.1 | 53.51%±2.17 | $10/$50 | 3m35s
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
10Claude Opus 4.8Anthropic53.22Board publisherSep 2026[1]
9 | Claude Opus 4.8 | 53.22%±2.17 | $5/$25 | 105.92s
11Gemini 3.6 FlashGoogle53.15Board publisherSep 2026[1]
10 | Gemini 3.6 Flash | 53.15%±2.16 | $1.5/$7.5 | 16.68s
12Claude Sonnet 5.5Anthropic · claude-sonnet-5-552.92Board publisherSep 2026[1]
11 | Claude Sonnet 5.5 | 52.92%±2.12 | $2/$10 | 3m59s
13GPT 5.1OpenAI52.73Board publisherSep 2026[1]
12 | GPT 5.1 | 52.73%±2.15 | $1.25/$10 | 54.55s
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
15Muse SparkMeta · muse_spark51.31Board publisherSep 2026[1]
14 | Muse Spark | 51.31%±2.24 | N/A | 2m03s
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
17Claude Opus 5.5Anthropic · claude-opus-5-549.80Board publisherSep 2026[1]
16 | Claude Opus 5.5 | 49.80%±2.27 | $4/$20 | 4m07s
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
19GPT 5OpenAI · gpt-5-2025-08-0749.63Board publisherSep 2026[1]
18 | GPT 5 | 49.63%±2.10 | $1.25/$10 | 58.27s
20Grok 4.7SpaceX AI · grok-4.749.55Board publisherSep 2026[1]
19 | Grok 4.7 | 49.55%±2.17 | $2/$6 | 3m33s
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
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
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
24GPT 5.5OpenAI · gpt-5.549.10Board publisherSep 2026[1]
23 | GPT 5.5 | 49.10%±2.19 | $5/$30 | 2m40s
25Kimi K3Moonshot AI · kimi-k348.88Board publisherSep 2026[1]
24 | Kimi K3 | 48.88%±2.19 | $3/$15 | 116.18s
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
27GPT-6 AstraOpenAI48.49Board publisherSep 2026[1]
26 | GPT-6 Astra | 48.49%±2.13 | $10/$50 | 102.86s
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
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
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
31Claude Sonnet 5Anthropic · claude-sonnet-547.54Board publisherSep 2026[1]
30 | Claude Sonnet 5 | 47.54%±2.27 | $2/$10 | 2m15s
32o3OpenAI · o3-2025-04-1647.29Board publisherSep 2026[1]
31 | o3 | 47.29%±2.16 | $2/$8 | 17.68s
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
34GPT-6 SolOpenAI · gpt-6-sol47.07Board publisherSep 2026[1]
33 | GPT-6 Sol | 47.07%±2.12 | $2/$10 | 62.71s
35MiniMax-M3MiniMax · MiniMax-M346.29Board publisherSep 2026[1]
34 | MiniMax-M3 | 46.29%±2.10 | $0.6/$2.4 | 63.12s
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
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
38Grok 4.6SpaceX AI · grok-4.644.71Board publisherSep 2026[1]
37 | Grok 4.6 | 44.71%±2.26 | $2/$6 | 2m07s
39GPT-6 LunaOpenAI · gpt-6-luna44.69Board publisherSep 2026[1]
38 | GPT-6 Luna | 44.69%±2.30 | $0.1/$0.5 | 108.77s
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
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
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
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
44Grok 4.5SpaceX AI · grok-4.543.29Board publisherSep 2026[1]
43 | Grok 4.5 | 43.29%±2.31 | $2/$6 | 59.64s
45Hy4 PreviewTencent · hy4-preview43.25Board publisherSep 2026[1]
44 | Hy4 Preview | 43.25%±2.13 | $0.834/$2.501 | 6m39s
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
47GLM 5.3Zhipu · glm-5.342.86Board publisherSep 2026[1]
46 | GLM 5.3 | 42.86%±2.11 | $1.4/$4.4 | 2m49s
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
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
50GLM 5.1Zhipu · glm-5.141.60Board publisherSep 2026[1]
49 | GLM 5.1 | 41.60%±2.12 | $1/$3.2 | 77.58s
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
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
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
54InklingThinking Machines · inkling41.19Board publisherSep 2026[1]
53 | Inkling | 41.19%±2.23 | $1/$4.05 | 2m47s
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
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
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
58GLM 5.2Zhipu · glm-5.240.77Board publisherSep 2026[1]
57 | GLM 5.2 | 40.77%±2.17 | $1.4/$4.4 | 95.27s
59Qwen 3.8 MaxAlibaba · qwen3.8-max40.67Board publisherSep 2026[1]
58 | Qwen 3.8 Max | 40.67%±2.03 | $2/$6 | 6m18s
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
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
62DeepSeek V4DeepSeek · deepseek-v4-pro40.45Board publisherSep 2026[1]
61 | DeepSeek V4 | 40.45%±2.12 | $1.32/$3.96 | 6m23s
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
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
65Kimi K2.6Moonshot AI · kimi-k2.640.14Board publisherSep 2026[1]
64 | Kimi K2.6 | 40.14%±2.04 | $0.95/$4 | 5m05s
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
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
68Nemotron 3 UltraNVIDIA · nemotron-3-ultra-550b-a55b38.62Board publisherSep 2026[1]
67 | Nemotron 3 Ultra | 38.62%±2.00 | N/A | 18.68s
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
70Grok 4SpaceX AI · grok-4-070938.08Board publisherSep 2026[1]
69 | Grok 4 | 38.08%±2.21 | $3/$15 | 89.00s
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
72Inkling SmallThinking Machines · inkling-small37.89Board publisherSep 2026[1]
71 | Inkling Small | 37.89%±2.21 | $0.3/$1.2 | 3m11s
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
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
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
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
77MiniMax-M2.7MiniMax · MiniMax-M2.734.44Board publisherSep 2026[1]
76 | MiniMax-M2.7 | 34.44%±1.99 | $0.3/$1.2 | 30.25s
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
79MiniMax-M2.1MiniMax · MiniMax-M2.134.08Board publisherSep 2026[1]
78 | MiniMax-M2.1 | 34.08%±1.94 | $0.3/$1.2 | 19.55s
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
81o4 MiniOpenAI · o4-mini-2025-04-1633.79Board publisherSep 2026[1]
80 | o4 Mini | 33.79%±2.02 | $1.1/$4.4 | 21.06s
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
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
84GLM 4.7Zhipu · glm-4.732.77Board publisherSep 2026[1]
83 | GLM 4.7 | 32.77%±2.00 | $0.6/$2.2 | 2m03s
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
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
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
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
89MiMo V2.5Xiaomi · mimo-v2.531.89Board publisherSep 2026[1]
88 | MiMo V2.5 | 31.89%±2.02 | $0.14/$0.28 | 17.70s
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
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
92Mercury 2.5Inception · mercury-2.531.33Board publisherSep 2026[1]
91 | Mercury 2.5 | 31.33%±1.95 | $0.2/$0.75 | 7.93s
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
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
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
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
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
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
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
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
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
102Laguna M.1Poolside · laguna-m.123.11Board publisherSep 2026[1]
101 | Laguna M.1 | 23.11%±1.69 | N/A | 71.00s
103Laguna XS.2Poolside · laguna-xs.221.25Board publisherSep 2026[1]
102 | Laguna XS.2 | 21.25%±1.70 | N/A | 33.09s
104Command A+Cohere · command-a-plus-05-202619.72Board publisherSep 2026[1]
103 | Command A+ | 19.72%±1.83 | N/A | 103.75s
1 document supports this board
- 1.Vals AI MedCode leaderboardofficial leaderboard, Vals AI, 29 Sep 2026. Every result it supports