# Vals MedCode (MedCode)

> Vals AI healthcare benchmark for whether models can support the medical billing process.

Canonical page: https://benchlm.ai/benchmarks/valsmedcode

- Category: [Agentic](/agentic)
- Last updated: September 26, 2026

## About MedCode

- Year: 2026
- Tasks: Medical billing support tasks
- Format: Accuracy score
- Difficulty: Professional healthcare administration
- Paper: [MedCode](https://www.vals.ai/benchmarks/medcode)

BenchLM mirrors the public Vals MedCode leaderboard as display-only healthcare evidence.

MedCode is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (102 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Claude Opus 5](/models/claude-opus-5) | Anthropic | 63.57% |
| 2 | [Gemini 3.1 Pro Preview](https://www.vals.ai/models/google_gemini-3.1-pro-preview) | Google | 59.06% |
| 3 | [Claude Fable 5](/models/claude-fable) | Anthropic | 56.07% |
| 4 | [Gemini 3 Flash Preview](https://www.vals.ai/models/google_gemini-3-flash-preview) | Google | 55.92% |
| 5 | [Gemini 3.5 Flash](/models/gemini-3-5-flash) | Google | 55.83% |
| 6 | [Claude Opus 4.7](/models/claude-opus-4-7) | Anthropic | 54.86% |
| 7 | [Claude Fable 5.1](/models/claude-fable-5-1) | Anthropic | 53.51% |
| 8 | [Gemini 3.7 Flash](/models/gemini-3-7-flash) | Google | 53.39% |
| 9 | [Claude Opus 4.8](/models/claude-opus-4-8) | Anthropic | 53.22% |
| 10 | [Gemini 3.6 Flash](/models/gemini-3-6-flash) | Google | 53.15% |
| 11 | [Claude Sonnet 5.5](/models/claude-sonnet-5-5) | Anthropic | 52.92% |
| 12 | [GPT-5.1](/models/gpt-5-1) | OpenAI | 52.73% |
| 13 | [Gemini 3 Pro Preview](https://www.vals.ai/models/google_gemini-3-pro-preview) | Google | 52.20% |
| 14 | [Muse Spark](/models/muse-spark) | Meta | 51.31% |
| 15 | [Gemini 2.5 Pro](/models/gemini-2-5-pro) | Google | 50.59% |
| 16 | [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | 49.80% |
| 17 | [GPT-5.2](/models/gpt-5-2) | OpenAI | 49.75% |
| 18 | [GPT-5](https://www.vals.ai/models/openai_gpt-5-2025-08-07) | OpenAI | 49.63% |
| 19 | [Grok 4.7](/models/grok-4-7) | xAI | 49.55% |
| 20 | [Muse Spark 1.2](/models/muse-spark-1-2) | Meta | 49.35% |
| 21 | [Claude Opus 4.5 Thinking](/models/claude-opus-4-5-thinking) | Anthropic | 49.16% |
| 22 | [Claude Opus 4.6 (Adaptive)](/models/claude-opus-4-6-thinking) | Anthropic | 49.13% |
| 23 | [GPT-5.5](/models/gpt-5-5) | OpenAI | 49.10% |
| 24 | [Kimi K3](/models/kimi-k3) | Moonshot AI | 48.88% |
| 25 | [GPT-6 Astra](/models/gpt-6-astra) | OpenAI | 48.49% |
| 26 | [Claude Opus 4.6](/models/claude-opus-4-6) | Anthropic | 48.24% |
| 27 | [Gemini 3.8 Flash](/models/gemini-3-8-flash) | Google | 48.13% |
| 28 | [Gemini 3.1 Flash Lite Preview](https://www.vals.ai/models/google_gemini-3.1-flash-lite-preview) | Google | 47.60% |
| 29 | [Claude Sonnet 5](/models/claude-sonnet-5) | Anthropic | 47.54% |
| 30 | [o3](/models/o3) | OpenAI | 47.29% |
| 31 | [Claude Opus 4.1 20250805 Thinking](https://www.vals.ai/models/anthropic_claude-opus-4-1-20250805-thinking) | Anthropic | 47.23% |
| 32 | [GPT-6 Sol](/models/gpt-6-sol) | OpenAI | 47.07% |
| 33 | [MiniMax M3](/models/minimax-m3) | MiniMax | 46.29% |
| 34 | [Claude Opus 4.5](/models/claude-opus-4-5) | Anthropic | 45.17% |
| 35 | [MiMo-V2.6-Pro](/models/mimo-v2-6-pro) | Xiaomi | 44.97% |
| 36 | [Grok 4.6](/models/grok-4-6) | xAI | 44.71% |
| 37 | [GPT-6 Luna](/models/gpt-6-luna) | OpenAI | 44.69% |
| 38 | [Claude Sonnet 4.5 Thinking](/models/claude-sonnet-4-5-thinking) | Anthropic | 44.13% |
| 39 | [GPT-5.6 Sol](/models/gpt-5-6-sol) | OpenAI | 43.97% |
| 40 | [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite) | Google | 43.49% |
| 41 | [GPT-5.6 Terra](/models/gpt-5-6-terra) | OpenAI | 43.41% |
| 42 | [Grok 4.5](/models/grok-4-5) | xAI | 43.29% |
| 43 | [Hy4 preview](/models/hy4-preview) | Tencent | 43.25% |
| 44 | [GPT-5 mini](/models/gpt-5-mini) | OpenAI | 43.05% |
| 45 | [GLM-5.3](/models/glm-5-3) | Z.AI | 42.86% |
| 46 | [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | DeepSeek | 42.47% |
| 47 | [GPT-5.6 Luna](/models/gpt-5-6-luna) | OpenAI | 42.39% |
| 48 | [GLM-5.1](/models/glm-5-1) | Z.AI | 41.60% |
| 49 | [DeepSeek V4 Flash 0731](/models/deepseek-v4-flash-0731) | DeepSeek | 41.41% |
| 50 | [Claude Opus 4.1](https://www.vals.ai/models/anthropic_claude-opus-4-1-20250805) | Anthropic | 41.37% |
| 51 | [GPT-5.4](/models/gpt-5-4) | OpenAI | 41.29% |
| 52 | [Inkling](/models/inkling) | Thinking Machines Lab | 41.19% |
| 53 | [DeepSeek V4.1 Flash](/models/deepseek-v4-1-flash) | DeepSeek | 41.17% |
| 54 | [MiMo-V2.6-Flash](/models/mimo-v2-6-flash) | Xiaomi | 41.06% |
| 55 | [GPT-5.4 nano](/models/gpt-5-4-nano) | OpenAI | 41.03% |
| 56 | [GLM-5.2](/models/glm-5-2) | Z.AI | 40.77% |
| 57 | [Qwen3.8 Max](/models/qwen3-8-max) | Alibaba | 40.67% |
| 58 | [Claude Sonnet 4.5](/models/claude-sonnet-4-5) | Anthropic | 40.57% |
| 59 | [Gemini 2.5 Flash Preview 09 2025](https://www.vals.ai/models/google_gemini-2.5-flash-preview-09-2025) | Google | 40.54% |
| 60 | [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | DeepSeek | 40.45% |
| 61 | [Gemini 2.5 Flash Thinking](https://www.vals.ai/models/google_gemini-2.5-flash-thinking) | Google | 40.36% |
| 62 | [Gemini 2.5 Flash Preview 09 2025 Thinking](https://www.vals.ai/models/google_gemini-2.5-flash-preview-09-2025-thinking) | Google | 40.33% |
| 63 | [Kimi K2.6](/models/kimi-2-6) | Moonshot AI | 40.14% |
| 64 | [Kimi K2.5 Thinking](https://www.vals.ai/models/kimi_kimi-k2.5-thinking) | Moonshot AI | 39.32% |
| 65 | [Qwen3.7 Max](/models/qwen3-7-max) | Alibaba | 38.75% |
| 66 | [Nemotron 3 Ultra 550b A55b](https://www.vals.ai/models/nvidia_nemotron-3-ultra-550b-a55b) | nvidia | 38.62% |
| 67 | [Gemini 2.5 Flash](/models/gemini-2-5-flash) | Google | 38.42% |
| 68 | [Grok 4 0709](https://www.vals.ai/models/grok_grok-4-0709) | xAI | 38.08% |
| 69 | [Grok 4.3](/models/grok-4-3) | xAI | 38.07% |
| 70 | [Inkling-Small](/models/inkling-small) | Thinking Machines Lab | 37.89% |
| 71 | [Grok 4 Fast (Reasoning)](/models/grok-4-fast-reasoning) | xAI | 37.38% |
| 72 | [Qwen3.6 Plus](/models/qwen3-6-plus) | Alibaba | 36.89% |
| 73 | [Llama4 Maverick Instruct Basic](https://www.vals.ai/models/fireworks_llama4-maverick-instruct-basic) | Fireworks | 36.51% |
| 74 | [Claude Sonnet 4 20250514 Thinking](https://www.vals.ai/models/anthropic_claude-sonnet-4-20250514-thinking) | Anthropic | 34.96% |
| 75 | [MiniMax M2.7](/models/minimax-m2-7) | MiniMax | 34.44% |
| 76 | [Gemini 2.5 Flash Lite Preview 09 2025 Thinking](https://www.vals.ai/models/google_gemini-2.5-flash-lite-preview-09-2025-thinking) | Google | 34.19% |
| 77 | [MiniMax M2.1](https://www.vals.ai/models/minimax_MiniMax-M2.1) | MiniMax | 34.08% |
| 78 | [Claude Sonnet 4](https://www.vals.ai/models/anthropic_claude-sonnet-4-20250514) | Anthropic | 33.94% |
| 79 | [O4 Mini](https://www.vals.ai/models/openai_o4-mini-2025-04-16) | OpenAI | 33.79% |
| 80 | [Mistral Medium 3.5](https://www.vals.ai/models/mistralai_mistral-medium-3.5) | Mistral | 33.75% |
| 81 | [Qwen3.5 Flash](/models/qwen3-5-flash) | Alibaba | 33.00% |
| 82 | [GLM-4.7](/models/glm-4-7) | Z.AI | 32.77% |
| 83 | [Claude Haiku 4.5 Thinking](/models/claude-haiku-4-5-thinking) | Anthropic | 32.68% |
| 84 | [MiMo-V2.5-Pro](/models/mimo-v2-5-pro) | Xiaomi | 32.48% |
| 85 | [Ling 3.0 Flash 2607](https://www.vals.ai/models/ant_ling-3.0-flash-2607) | ant | 32.27% |
| 86 | [Grok 4.20 0309 Reasoning](https://www.vals.ai/models/grok_grok-4.20-0309-reasoning) | xAI | 32.16% |
| 87 | [MiMo-V2.5](/models/mimo-v2-5) | Xiaomi | 31.89% |
| 88 | [Qwen3 VL Plus](https://www.vals.ai/models/alibaba_qwen3-vl-plus-2025-09-23) | Alibaba | 31.65% |
| 89 | [Qwen3 Max](/models/qwen3-max) | Alibaba | 31.37% |
| 90 | [Mercury 2.5](/models/mercury-2-5) | Inception | 31.33% |
| 91 | [GPT-5 nano](/models/gpt-5-nano) | OpenAI | 30.44% |
| 92 | [Grok 4 Fast Non Reasoning](https://www.vals.ai/models/grok_grok-4-fast-non-reasoning) | xAI | 30.04% |
| 93 | [Ling 3.0 Flash Af Rc3](https://www.vals.ai/models/ant_ling-3.0-flash-af-rc3) | ant | 29.30% |
| 94 | [Qwen3.8-27B](/models/qwen3-8-27b) | Alibaba | 28.70% |
| 95 | [Grok 4.1 Fast Non Reasoning](https://www.vals.ai/models/grok_grok-4-1-fast-non-reasoning) | xAI | 28.35% |
| 96 | [Grok 4.1 Fast (Reasoning)](/models/grok-4-1-fast-reasoning) | xAI | 28.08% |
| 97 | [Gemini 2.5 Flash Lite](https://www.vals.ai/models/google_gemini-2.5-flash-lite) | Google | 27.11% |
| 98 | [Gemini 2.5 Flash Lite Preview 09 2025](https://www.vals.ai/models/google_gemini-2.5-flash-lite-preview-09-2025) | Google | 27.08% |
| 99 | [Meta Llama Llama 4 Scout 17B 16E Instruct](https://www.vals.ai/models/together_meta-llama/Llama-4-Scout-17B-16E-Instruct) | Together AI | 23.31% |
| 100 | [Laguna M.1](/models/laguna-m-1) | Poolside | 23.11% |
| 101 | [Laguna XS.2](/models/laguna-xs-2) | Poolside | 21.25% |
| 102 | [Command A Plus 05 2026](https://www.vals.ai/models/cohere_command-a-plus-05-2026) | Cohere | 19.72% |

## FAQ

### What does MedCode measure?

Vals AI healthcare benchmark for whether models can support the medical billing process.

### Which model leads the published MedCode snapshot?

Claude Opus 5 currently leads the published MedCode snapshot with a score of 63.57%.

### How many models are evaluated on MedCode?

The September 26, 2026 contains 102 AI models.

### Does MedCode affect BenchLM's overall score?

Not directly. MedCode is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.