MedCode leaderboard

Assigning the right medical billing codes from clinical notes. Claude Opus 5 leads with 63.57%.

Models
97
Leader
Claude Opus 5
Source
Vals AI
As of
Oct 24, 2026
  1. 1Claude Opus 563.6%
  2. 2Gemini 3.1 Pro Preview59.1%
  3. 3Gemini 4 Argon58.8%
  4. 4Claude Fable 556.1%
  5. 5Gemini 3 Flash55.9%
  6. 6Gemini 3.5 Flash55.8%
  7. 7Claude Opus 4.754.9%
  8. 8Claude Fable 5.153.5%
  9. 9Gemini 3.7 Flash53.4%
  10. 10Claude Opus 4.853.2%
MedCode, accuracy against cost per test
Open weightsProprietaryBest for the price
10%25%40%55%70%$.1$1$10Cost per test, log scale →Claude Opus 5Gemini 3.1 Pro PreviewGemini 3 FlashClaude Haiku 5.5Ling 3.0 Flash

Full leaderboard

RankModelLabAccuracyCost / testHarnessPrice in / out
1Claude Opus 5Anthropic63.57%$5 / $25—$5 / $25
2Gemini 3.1 Pro PreviewGoogle59.06%$2 / $12—$2 / $12
3Gemini 4 ArgonGoogle58.80%$4 / $20—$2 / $10
4Claude Fable 5Anthropic56.07%$10 / $50—$10 / $50
5Gemini 3 FlashGoogle55.92%$0.5 / $3—$0.50 / $3
6Gemini 3.5 FlashGoogle55.83%$1.5 / $9—$1.50 / $9
7Claude Opus 4.7Anthropic54.86%$5 / $25—$5 / $25
8Claude Fable 5.1Anthropic53.51%$10 / $50—$10 / $50
9Gemini 3.7 FlashGoogle53.39%$1.5 / $7.5—$0.75 / $3.75
10Claude Opus 4.8Anthropic53.22%$5 / $25—$5 / $25
11Gemini 3.6 FlashGoogle53.15%$1.5 / $7.5—$0.75 / $3.75
12Claude Sonnet 5.5Anthropic52.92%$2 / $10—$2 / $10
13GPT-5.1OpenAI52.73%$1.25 / $10—$1.25 / $10
14Gemini 3 ProGoogle52.20%$2 / $12——
15Claude Haiku 5.5Anthropic51.54%$0.1 / $0.5—$0.10 / $0.50
16Muse SparkMeta51.31%N/A——
17Gemini 2.5 ProGoogle50.59%$1.25 / $10—$1.25 / $10
18Muse Wonder FullMeta49.93%$4 / $20——
19Claude Opus 5.5Anthropic49.80%$4 / $20—$4 / $20
20GPT-5.2OpenAI49.75%$1.75 / $14—$1.75 / $14
21GPT-5OpenAI49.63%$1.25 / $10—$1.25 / $10
22Grok 4.7xAI49.55%$2 / $6—$2 / $6
23Kimi K3Moonshot AI49.36%$3 / $15—$0.24 / $11
24Muse Spark 1.2Meta49.35%$1.25 / $4.25—$1.25 / $4.25
27GPT-5.5OpenAI49.10%$5 / $30—$5 / $30
28GPT-6.1 SolOpenAI48.84%$2 / $10—$2 / $10
29GPT-6 AstraOpenAI48.49%$10 / $50—$10 / $50
30Claude Opus 4.6Anthropic48.24%$5 / $25—$5 / $25
31Gemini 3.8 FlashGoogle48.13%$1.5 / $7.5—$0.82 / $4.13
32Gemini 3.1 Flash-Lite PreviewGoogle47.60%$0.25 / $1.5—$0.25 / $1.50
33Claude Sonnet 5Anthropic47.54%$2 / $10—$2 / $10
34o3OpenAI47.29%$2 / $8—$2 / $8
36GPT-6 SolOpenAI47.07%$2 / $10—$2 / $10
37MiniMax-M3MiniMax46.29%$0.6 / $2.4—$0.30 / $1.20
38Claude Opus 4.5Anthropic45.17%$5 / $25—$5 / $25
39MiMo-V2.6-ProXiaomi44.97%$0.435 / $0.87—$0.43 / $0.87
40Grok 4.6xAI44.71%$2 / $6—$2 / $6
41GPT-6 LunaOpenAI44.69%$0.1 / $0.5—$0.10 / $0.50
43GPT-5.6 SolOpenAI43.97%$4 / $20—$4 / $20
44Gemini 3.5 Flash-LiteGoogle43.49%$0.3 / $2.5—$0.30 / $2.50
45GPT-5.6 TerraOpenAI43.41%$2 / $12—$2 / $12
46Grok 4.5xAI43.29%$2 / $6—$2 / $6
47Hy4 previewTencent43.25%$0.834 / $2.501—$0.75 / $2.25
48GPT-5 miniOpenAI43.05%$0.25 / $2—$0.25 / $2
49GLM-5.3Z.ai42.86%$1.4 / $4.4—$0.079 / $1.40
51GPT-5.6 LunaOpenAI42.39%$0.2 / $1.2—$0.20 / $1.20
52GLM-5.1Z.ai41.60%$1 / $3.2—$1.40 / $4.40
53DeepSeek-V4-FlashDeepSeek41.41%$0.44 / $1.32—$0.042 / $0.18
54Claude Opus 4.1Anthropic41.37%$15 / $75—$15 / $75
55GPT-5.4OpenAI41.29%$2.5 / $15—$2.50 / $15
56InklingThinky41.19%$1 / $4.05—$1 / $4.05
57DeepSeek-V4.1-Flash-20260910DeepSeek41.17%$0.3 / $1.2—$0.15 / $0.60
58MiMo-V2.6-FlashXiaomi41.06%$0.14 / $0.28—$0.14 / $0.28
59GPT-5.4 nanoOpenAI41.03%$0.2 / $1.25—$0.20 / $1.25
60GLM-5.2Z.ai40.77%$1.4 / $4.4—$0.034 / $7
61Mistral Large 4Mistral AI40.69%$1.36 / $4.18—$1.36 / $4.18
62Qwen3.8-MaxAlibaba40.67%$2 / $6—$2 / $6
63Claude Sonnet 4.5Anthropic40.57%$3 / $15—$3 / $15
65DeepSeek-V4-ProDeepSeek40.45%$1.32 / $3.96—$0.66 / $1.98
66Gemini 2.5 Flash Preview 4/17Google40.36%$0.3 / $2.5——
68Kimi K2.6Moonshot AI40.14%$0.95 / $4—$0.65 / $3.41
69Kimi K2.5Moonshot AI39.32%$0.6 / $3—$0.50 / $2.50
70Qwen3.7-Max-PreviewAlibaba38.75%$2.5 / $7.5—$1.48 / $4.42
71Nemotron 3 UltraNVIDIA38.62%N/A—$0.60 / $2.40
72Gemini 2.5 FlashGoogle38.42%$0.3 / $2.5—$0.30 / $2.50
73Grok 4xAI38.08%$3 / $15——
74Grok 4.3xAI38.07%$1.25 / $2.5—$1.25 / $2.50
75Inkling-SmallThinky37.89%$0.3 / $1.2—$0.45 / $1.20
77Qwen3.6-PlusAlibaba36.89%$0.5 / $3—$0.33 / $1.95
78Llama 4 MaverickFireworks AI36.51%$0.22 / $0.88—$0.19 / $0.65
80MiniMax-M2.7MiniMax34.44%$0.3 / $1.2—$0.30 / $1.20
82MiniMax-M2.1 PreviewMiniMax34.08%$0.3 / $1.2—$0.30 / $1.20
83Claude Sonnet 4Anthropic33.94%$3 / $15——
84o4-miniOpenAI33.79%$1.1 / $4.4—$1.10 / $4.40
85Mistral Medium 3.5Mistral AI33.75%$1.5 / $7.5—$1.50 / $7.50
86Qwen3.5-FlashAlibaba33.00%$0.1 / $0.4—$0.065 / $0.26
87GLM-4.7Z.ai32.77%$0.6 / $2.2—$0.54 / $1.98
88Claude Haiku 4.5Anthropic32.68%$1 / $5—$1 / $5
89MiMo-V2.5-ProXiaomi32.48%$0.435 / $0.87—$0.30 / $0.61
90Ling 3.0 FlashinclusionAI32.27%$0.075 / $0.22—$0.021 / $0.063
91Grok 4.20xAI32.16%$2 / $6—$1.25 / $2.50
92MiMo-V2.5Xiaomi31.89%$0.14 / $0.28—$0.12 / $0.24
93Qwen 3 VL PlusAlibaba31.65%$0.2 / $1.6——
94Qwen3-Max-PreviewAlibaba31.37%$1.2 / $6——
95Mercury 2.5Inception31.33%$0.2 / $0.75—$0.04 / $0.15
96GPT-5 nanoOpenAI30.44%$0.05 / $0.4—$0.05 / $0.40
97Grok 4 FastxAI30.04%$0.2 / $0.5——
98Ling 3.0 Flash Fin—29.30%$0.06 / $0.18——
99Qwen3.8-27BAlibaba28.70%$0.5 / $3—$0.20 / $2.50
100Grok 4.1 Fast Non-ReasoningxAI28.35%$0.2 / $0.5——
101Grok 4.1 FastxAI28.08%$0.2 / $0.5——
102Gemini 2.5 Flash-Lite PreviewGoogle27.11%$0.1 / $0.4—$0.10 / $0.40
103Gemini 2.5 Flash PreviewGoogle27.08%$0.1 / $0.4——
104Llama 4 ScoutMeta23.31%$0.18 / $0.59—$0.10 / $0.30
105Laguna M.1Poolside23.11%N/A——
106Laguna XS.2Poolside21.25%N/A——
107Command ACohere19.72%N/A—$0.30 / $1.50

Related leaderboards

Sources

  • Vals AI, as of Oct 24, 2026
  • Provider list prices, as of Oct 24, 2026

Every number on this page comes from these sources; models without a published number show none. Download the data. Cite as “Nexus Explorer, nexus.inc/models”.