Best LLM
What is the best LLM for medical tasks?
Claude Opus 5, Claude Fable 5.1, Claude Sonnet 5.5 and 1 other are practically level at the top in medical tasks.
Among the ten best, Claude Haiku 5.5 is the cheapest at $0.20 per million tokens.
The fastest among them is Claude Haiku 5.5, at 164 tokens per second.
- Ranked models
- 72
- Tests
- 3
- Data as of
- Nov 10, 2026
Ranking: Medicine
Place and value in the area, plus overall index, price and speed. Higher values are better.
| Rank | Model | Value | Overall index | Price (3:1) | Speed |
|---|---|---|---|---|---|
| 1 | Claude Opus 5Top group | 130.4 | 117.4 | $10 | 71 |
| 2 | Claude Fable 5.1Top group | 123.4 | 124.1 | $20 | 59 |
| 3 | Gemini 4 ArgonUpper group | 123.1 | 121.4 | $4 | 46 |
| 4 | Claude Sonnet 5.5Upper group | 122.1 | 121.8 | $4 | 103 |
| 5 | Claude Opus 5.5Upper group | 120.9 | 125.6 | $8 | 75 |
| 6 | Claude Fable 5Upper group | 118.0 | 112.8 | $20 | 50 |
| 7 | Muse Wonder FullMiddle group | 114.6 | 118.1 | n/a | n/a |
| 8 | GPT-6 AstraMiddle group | 113.4 | 120.2 | $20 | 58 |
| 9 | GPT-6.1 SolMiddle group | 110.7 | 118.0 | $4 | 44 |
| 10 | Claude Haiku 5.5Middle group | 110.7 | 102.8 | $0.20 | 164 |
| 11 | Grok 4.7Middle group | 107.7 | 103.3 | $3 | 47 |
| 12 | Gemini 3.7 FlashMiddle group | 106.9 | 107.9 | n/a | 72 |
| 13 | Claude Opus 4.8Middle group | 106.7 | 99.5 | $10 | 71 |
| 14 | Kimi K3Middle group | 105.1 | 101.1 | $6 | 61 |
| 15 | GPT-5.5Middle group | 103.9 | 101.5 | $11.25 | 87 |
| 16 | Claude Opus 4.7Middle group | 103.4 | 95.1 | $10 | 57 |
| 17 | Gemini 3.8 FlashMiddle group | 102.1 | 106.8 | $1.50 | 81 |
| 18 | GPT-6 SolMiddle group | 102.0 | 109.1 | $4 | 82 |
| 19 | GPT-5.6 SolMiddle group | 101.1 | 109.1 | $8 | 75 |
| 20 | MiMo V2.6 ProMiddle group | 101.0 | 100.4 | $0.54 | 32 |
Show all 72 ranked models
| Rank | Model | Value | Overall index | Price (3:1) | Speed |
|---|---|---|---|---|---|
| 21 | GLM-5.3Middle group | 99.8 | 100.6 | $2.15 | 81 |
| 22 | Gemini 3.5 FlashMiddle group | 99.6 | 97.8 | n/a | 142 |
| 23 | Grok 4.6Middle group | 99.5 | 102.1 | $3 | 58 |
| 24 | Gemini 3.6 FlashMiddle group | 99.1 | 97.6 | $1.50 | 110 |
| 25 | Gemini 3.1 Pro PreviewMiddle group | 95.7 | 91.4 | $4.50 | 96 |
| 26 | Grok 4.5Middle group | 95.3 | 94.8 | $3 | 52 |
| 27 | GPT-5.6 TerraMiddle group | 94.9 | 100.8 | $4.50 | 72 |
| 28 | Hy4 previewMiddle group | 94.5 | n/a | n/a | n/a |
| 29 | GPT-6 LunaMiddle group | 94.5 | 95.8 | $0.20 | 77 |
| 30 | Claude Opus 4.6Middle group | 94.3 | 84.2 | $10 | 36 |
| 31 | DeepSeek-V4.1-FlashMiddle group | 93.8 | 99.5 | $0.26 | 118 |
| 32 | MiMo V2.6 FlashMiddle group | 93.4 | 97.3 | $0.18 | 38 |
| 33 | MiniMax M3Middle group | 93.3 | 83.0 | $0.52 | 82 |
| 34 | Qwen 3.8 Max 0902Middle group | 93.0 | 100.8 | $2.48 | 36 |
| 35 | GPT-5.6 LunaMiddle group | 91.7 | 93.8 | $0.45 | 123 |
| 36 | Claude Sonnet 5Middle group | 89.9 | 92.1 | $4 | 77 |
| 37 | DeepSeek V4 Pro 0813Middle group | 89.4 | n/a | n/a | n/a |
| 38 | GPT-5Middle group | 87.9 | 77.5 | $3.44 | 83 |
| 39 | GLM-5.2Middle group | 87.0 | 89.0 | $2.15 | 73 |
| 40 | DeepSeek V4 Flash 0731Middle group | 87.0 | n/a | n/a | n/a |
| 41 | Gemini 3 Flash PreviewMiddle group | 85.6 | 81.0 | $1.13 | 101 |
| 42 | InklingLower group | 81.2 | 72.1 | $1.76 | n/a |
| 43 | GPT-5.4Lower group | 80.6 | 86.5 | $5.63 | 58 |
| 44 | o3Lower group | 80.3 | 74.2 | $3.50 | 73 |
| 45 | Kimi K2.6Lower group | 79.9 | 84.9 | $1.71 | 32 |
| 46 | DeepSeek-V4-ProLower group | 79.6 | 87.2 | $0.99 | 44 |
| 47 | Qwen 3.7 MaxLower group | 79.5 | 85.4 | $2.48 | 50 |
| 48 | Claude Opus 4.5Lower group | 79.4 | 74.4 | $10 | 44 |
| 49 | Gemini 2.5 ProLower group | 77.2 | 61.4 | $3.44 | 74 |
| 50 | Claude Sonnet 4.5Lower group | 77.1 | 65.9 | $6 | 38 |
| 51 | GLM-5.1Lower group | 77.0 | 82.8 | $2.15 | 39 |
| 52 | GPT-5 miniLower group | 76.4 | 65.8 | $0.69 | 105 |
| 53 | Inkling SmallLower group | 74.7 | 68.7 | $0.52 | 61 |
| 54 | Gemini 3.5 Flash-LiteLower group | 73.4 | 73.7 | $0.85 | 145 |
| 55 | GPT-5.4 nanoLower group | 71.7 | 64.0 | $0.46 | 98 |
| 56 | Qwen 3.8 27BLower group | 71.6 | 82.8 | $0.66 | 66 |
| 57 | MiMo-V2.5-ProLower group | 70.9 | 73.0 | $0.54 | 59 |
| 58 | Kimi K2.5Lower group | 70.2 | 70.3 | $1.14 | 37 |
| 59 | Grok 4.3Lower group | 68.3 | 71.6 | $1.56 | 66 |
| 60 | MiniMax M2.7Lower group | 66.3 | 65.1 | $0.37 | 45 |
| 61 | o4-miniLower group | 62.2 | 63.5 | n/a | n/a |
| 62 | MiMo-V2.5Lower group | 60.8 | 69.1 | $0.18 | 55 |
| 63 | MiniMax M2.1Lower group | 60.7 | 57.3 | $0.52 | n/a |
| 64 | Ling 3.0 FlashLower group | 57.2 | 47.9 | $0.032 | 106 |
| 65 | GLM-4.7Lower group | 55.3 | 56.2 | $0.78 | 25 |
| 66 | Grok 4.20 ReasoningLower group | 52.7 | 58.3 | $1.56 | 66 |
| 67 | Mistral Medium 3.5Lower group | 49.7 | 46.3 | $3 | 118 |
| 68 | GPT-5 nanoLower group | 46.5 | 32.4 | $0.14 | 136 |
| 69 | Mercury 2.5Lower group | 40.9 | 45.3 | n/a | n/a |
| 70 | Laguna XS.2Lower group | 22.2 | n/a | n/a | n/a |
| 71 | Command A PlusLower group | 18.7 | 30.7 | n/a | n/a |
| 72 | Llama 4 ScoutLower group | 5.0 | 4.7 | $0.15 | 62 |
Price in dollars per million tokens, mixed from 3 parts input and 1 part output. Speed in tokens per second.
Claude Opus 5Rank 1130.4
Claude Fable 5.1Rank 2123.4
Gemini 4 ArgonRank 3123.1
Claude Sonnet 5.5Rank 4122.1
Claude Opus 5.5Rank 5120.9
Claude Fable 5Rank 6118.0
Muse Wonder FullRank 7114.6
GPT-6 AstraRank 8113.4
GPT-6.1 SolRank 9110.7
Claude Haiku 5.5Rank 10110.7
Grok 4.7Rank 11107.7
Gemini 3.7 FlashRank 12106.9
Claude Opus 4.8Rank 13106.7
Kimi K3Rank 14105.1
GPT-5.5Rank 15103.9
Claude Opus 4.7Rank 16103.4
Gemini 3.8 FlashRank 17102.1
GPT-6 SolRank 18102.0
GPT-5.6 SolRank 19101.1
MiMo V2.6 ProRank 20101.0
Which tests count here?
3 tests by independent evaluators feed this area. Each test counts with the result of the model in question.
Popular comparisons among the best
Other tasks
All LLMs comparedHow the overall index worksCompare several models