LLM Leaderboard
Benchmark Scores for Frontier AI Models
LM Intelligence Index
62.2
#1 of 63 models
463 scores 63 models 8 benchmarksSource-linked scores · LM Board computes the Index
LM Board runs no evaluations. Artificial Analysis (opens in a new tab) publishes 463 of the 463 benchmark scores; no scores are vendor-published. LM Board computes the Index and ranks from those published scores.
Every score links to the measurement it came from, with the date it was retrieved and the settings it was run under. Every model name opens its complete citation record; where the full table fits, score numerals open their source details directly.
Scores retrieved Aug 5, 2026 · 11 models released in the last 45 days
Showing 63 of 63 models. Sorted by LM Intelligence Index, descending. Showing table projection.
12 columns. Use arrow keys to move through cells, Enter to activate the primary action, and F2 then Tab to reach every action in the current cell. Escape returns to the grid.
Currently sorted descending.
| 1 | Evidence 7 scores | 62.2 | 89.1 | 30.3 | 70.0 | 52.6 | 93.2 | 55.7 | — | 29.1 | $5.0 / $25.0 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | Evidence 8 scores | 62.1 | 88.0 | 33.0 | 73.7 | 47.2 | 94.1 | 56.1 | 72.7 | 32.3 | $5.0 / $30.0 |
| 3 | Evidence 7 scores | 61.7 | 85.0 | 33.4 | 74.7 | 44.4 | 93.5 | 58.7 | — | 23.4 | $3.0 / $15.0 |
| 4 | Evidence 8 scores | 60.9 | 84.3 | 31.3 | 74.3 | 44.3 | 93.5 | 56.1 | 75.9 | 27.1 | $5.0 / $30.0 |
| 5 | Evidence 8 scores | 60.4 | 88.0 | 31.8 | 74.0 | 41.8 | 92.5 | 53.9 | 71.2 | 30.0 | $2.0 / $12.0 |
| 6 | Evidence 8 scores | 60.0 | 84.6 | 26.8 | 70.0 | 53.3 | 92.6 | 60.2 | 63.5 | 28.6 | $10.0 / $50.0 |
| 7 | Evidence 8 scores | 58.8 | 78.3 | 30.3 | 74.0 | 41.6 | 92.0 | 56.6 | 74.0 | 23.4 | $2.5 / $15.0 |
| 8 | Evidence 7 scores | 57.6 | 81.7 | 32.6 | 67.7 | 40.3 | 93.1 | 54.1 | — | 15.4 | $2.0 / $6.0 |
| 9 | Evidence 6 scores | 57.5 | — | — | 74.0 | 39.9 | 91.5 | 53.2 | 75.4 | 16.9 | $1.8 / $14.0 |
| 10 | Evidence 7 scores | 57.4 | 80.9 | 27.2 | 74.0 | 37.2 | 91.1 | 52.6 | — | 20.6 | $0.20 / $1.2 |
| 11 | Evidence 7 scores | 57.1 | 80.5 | 28.3 | 70.7 | 39.6 | 91.1 | 53.6 | — | 16.9 | $2.0 / $10.0 |
| 12 | #12Gemini 3.1 Pro PreviewGoogle Evidence 8 scores | 56.9 | 73.8 | 16.5 | 72.7 | 44.7 | 94.1 | 58.9 | 77.1 | 17.7 | $2.0 / $12.0 |
| 13 | Evidence 8 scores | 56.8 | 84.6 | 27.6 | 67.7 | 45.7 | 92.0 | 53.5 | 62.2 | 20.9 | $5.0 / $25.0 |
| 14 | Evidence 8 scores | 56.3 | 77.9 | 26.8 | 71.3 | 40.1 | 89.5 | 50.5 | 73.3 | 20.9 | $1.4 / $4.4 |
| 15 | Evidence 7 scores | 56.1 | 77.9 | 25.2 | 63.3 | 45.1 | 89.8 | 58.2 | — | 15.1 | $1.3 / $4.3 |
| 16 | Evidence 8 scores | 56.1 | 78.7 | 25.4 | 69.3 | 41.0 | 92.2 | 53.1 | 76.3 | 13.1 | $1.5 / $9.0 |
| 17 | Evidence 7 scores | 55.4 | 78.7 | 31.1 | 65.7 | 36.8 | 90.8 | 49.9 | — | 16.6 | $0.14 / $0.28 |
| 18 | Evidence 6 scores | 55.2 | — | — | 72.7 | 35.5 | 90.3 | 52.1 | 75.4 | 11.6 | $1.8 / $14.0 |
| 19 | Evidence 7 scores | 55.1 | 77.5 | 24.5 | 69.7 | 38.3 | 92.8 | 52.7 | — | 10.6 | $1.5 / $7.5 |
| 20 | Evidence 8 scores | 54.8 | 83.2 | 28.9 | 70.3 | 39.6 | 91.4 | 54.5 | 58.6 | 12.0 | $5.0 / $25.0 |
| 21 | Evidence 6 scores | 54.8 | — | — | 70.7 | 37.2 | 90.8 | 56.1 | 70.4 | 9.1 | — |
| 22 | #22Qwen3.7-MaxQwen Evidence 8 scores | 53.5 | 74.5 | 10.9 | 69.0 | 38.1 | 92.3 | 48.8 | 80.5 | 13.4 | $2.5 / $7.5 |
| 23 | #23Kimi K2.6Moonshot AI Evidence 8 scores | 52.6 | 65.9 | 20.6 | 69.7 | 35.9 | 91.1 | 53.5 | 76.0 | 8.0 | $0.95 / $4.0 |
| 24 | Evidence 8 scores | 52.5 | 64.0 | 25.8 | 66.3 | 35.9 | 88.8 | 50.0 | 76.5 | 12.9 | $0.44 / $0.87 |
| 25 | #25Muse SparkMeta Evidence 8 scores | 52.3 | 62.2 | 19.6 | 69.7 | 39.9 | 88.4 | 51.5 | 75.9 | 11.3 | — |
| 26 | #26MiniMax M3MiniMax Evidence 8 scores | 51.8 | 65.2 | 13.0 | 74.0 | 37.1 | 92.9 | 45.4 | 82.9 | 3.7 | $0.30 / $1.2 |
| 27 | Evidence 6 scores | 51.1 | — | — | 70.7 | 36.7 | 89.6 | 51.9 | 53.1 | 12.6 | $5.0 / $25.0 |
| 28 | Evidence 6 scores | 50.3 | — | — | 58.0 | 32.2 | 91.1 | 45.6 | 81.2 | 6.6 | $1.3 / $2.5 |
| 29 | Evidence 8 scores | 50.0 | 61.8 | 22.9 | 63.0 | 32.1 | 89.4 | 44.9 | 79.2 | 7.1 | $0.14 / $0.28 |
| 30 | Evidence 8 scores | 49.7 | 59.2 | 21.4 | 69.3 | 26.7 | 87.5 | 49.9 | 73.3 | 10.0 | $0.75 / $4.5 |
| 31 | Evidence 8 scores | 49.5 | 71.2 | 30.5 | 70.7 | 30.0 | 87.5 | 46.8 | 56.6 | 3.1 | $3.0 / $15.0 |
| 32 | #32Kimi K2.7 CodeMoonshot AI Evidence 8 scores | 49.4 | 67.4 | 18.1 | 66.3 | 32.8 | 89.6 | 47.5 | 63.1 | 10.0 | $0.95 / $4.0 |
| 33 | Evidence 8 scores | 48.5 | 60.7 | 21.0 | 66.0 | 26.5 | 81.7 | 46.9 | 75.9 | 9.3 | $0.20 / $1.3 |
| 34 | Evidence 6 scores | 48.3 | — | — | 74.0 | 28.4 | 86.6 | 49.5 | 58.0 | 4.6 | $5.0 / $25.0 |
| 35 | #35Qwen3.6-PlusQwen Evidence 8 scores | 47.5 | 61.4 | 16.5 | 69.7 | 25.7 | 88.2 | 40.7 | 75.2 | 2.9 | $0.50 / $3.0 |
| 36 | Evidence 8 scores | 47.0 | 52.4 | 14.0 | 75.0 | 26.5 | 87.3 | 43.3 | 72.9 | 4.9 | $1.3 / $10.0 |
| 37 | Evidence 8 scores | 46.9 | 61.8 | 11.6 | 62.3 | 28.0 | 86.8 | 43.8 | 76.3 | 4.6 | $1.4 / $4.4 |
| 38 | Evidence 8 scores | 46.5 | 53.9 | 13.8 | 67.0 | 26.6 | 86.7 | 39.9 | 81.4 | 3.1 | — |
| 39 | Evidence 8 scores | 46.2 | 51.3 | 13.4 | 65.7 | 27.3 | 89.3 | 42.0 | 78.8 | 1.7 | $0.60 / $3.6 |
| 40 | Evidence 6 scores | 46.1 | — | — | 63.3 | 27.3 | 82.0 | 46.2 | 72.3 | 2.0 | $1.0 / $3.2 |
| 41 | Evidence 8 scores | 45.6 | 45.7 | 14.2 | 65.3 | 29.4 | 87.9 | 49.0 | 70.2 | 3.1 | $0.60 / $3.0 |
| 42 | Evidence 8 scores | 45.5 | 35.2 | 19.6 | 75.6 | 26.5 | 85.4 | 42.9 | 73.1 | 5.7 | $1.3 / $10.0 |
| 43 | #43o3OpenAI Evidence 6 scores | 44.7 | — | — | 69.3 | 20.0 | 82.7 | 41.0 | 71.4 | 1.1 | $2.0 / $8.0 |
| 44 | #44Grok 4xAI Evidence 6 scores | 44.7 | — | — | 68.0 | 23.9 | 87.7 | 45.7 | 53.7 | 2.0 | — |
| 45 | #45Kimi K2 ThinkingMoonshot AI Evidence 6 scores | 44.5 | — | — | 66.3 | 22.3 | 83.8 | 42.4 | 68.1 | 2.6 | — |
| 46 | Evidence 8 scores | 43.0 | 55.8 | 19.0 | 65.7 | 17.3 | 83.4 | 44.7 | 57.3 | 1.1 | $3.0 / $15.0 |
| 47 | Evidence 6 scores | 42.5 | — | — | 68.0 | 17.6 | 85.3 | 44.2 | 52.7 | 2.9 | — |
| 48 | Evidence 8 scores | 42.4 | 46.8 | 18.8 | 65.0 | 22.2 | 84.0 | 38.9 | 60.7 | 2.9 | — |
| 49 | #49Gemini 3.5 Flash-LiteGoogle Evidence 7 scores | 41.2 | 53.6 | 16.5 | 62.0 | 17.5 | 83.8 | 40.9 | — | 0.0 | $0.30 / $2.5 |
| 50 | #50Mistral Medium 3.5Mistral AI Evidence 8 scores | 40.2 | 50.6 | 14.4 | 61.0 | 12.8 | 74.9 | 39.6 | 68.8 | 0.0 | $1.5 / $7.5 |
| 51 | #51MiniMax M2MiniMax Evidence 6 scores | 40.1 | — | — | 61.0 | 12.5 | 77.7 | 36.1 | 72.3 | 0.9 | $0.30 / $1.2 |
| 52 | Evidence 6 scores | 39.7 | — | — | 66.3 | 11.9 | 80.9 | 40.9 | 55.4 | 0.0 | $15.0 / $75.0 |
| 53 | #53Gemini 2.5 ProGoogle Evidence 8 scores | 37.9 | 28.5 | 9.3 | 66.0 | 21.1 | 84.4 | 42.8 | 48.7 | 2.6 | $1.3 / $10.0 |
| 54 | Evidence 8 scores | 37.3 | 44.2 | 9.1 | 70.3 | 9.7 | 67.2 | 43.3 | 54.3 | 0.0 | $1.0 / $5.0 |
| 55 | Evidence 8 scores | 36.8 | 26.2 | 12.0 | 50.7 | 18.5 | 78.2 | 38.9 | 69.0 | 1.1 | — |
| 56 | #56DeepSeek R1 0528DeepSeek Evidence 6 scores | 36.2 | — | — | 54.7 | 14.9 | 81.3 | 40.3 | 39.6 | 1.4 | — |
| 57 | Evidence 8 scores | 36.1 | 49.4 | 10.5 | 54.3 | 13.4 | 78.0 | 38.4 | 43.4 | 1.1 | $0.60 / $2.2 |
| 58 | #58Qwen3-MaxQwen Evidence 6 scores | 32.1 | — | — | 46.7 | 11.1 | 76.4 | 38.3 | 44.2 | 0.0 | $1.2 / $6.0 |
| 59 | #59Llama 4 MaverickMeta Evidence 8 scores | 25.7 | 7.9 | 3.9 | 46.0 | 4.8 | 67.1 | 33.1 | 43.0 | 0.0 | — |
| 60 | #60Devstral 2Mistral AI Evidence 8 scores | 25.6 | 30.3 | 10.3 | 30.0 | 3.6 | 59.4 | 33.1 | 38.1 | 0.0 | — |
| 61 | #61Mistral Large 3Mistral AI Evidence 8 scores | 24.6 | 12.0 | 5.8 | 34.7 | 4.1 | 68.0 | 36.2 | 36.2 | 0.0 | $0.50 / $1.5 |
| 62 | Evidence 6 scores | 23.8 | — | — | 7.3 | 8.1 | 72.8 | 34.7 | 38.2 | 0.0 | — |
| 63 | #63Llama 4 ScoutMeta Evidence 8 scores | 19.0 | 3.8 | 3.3 | 25.8 | 4.3 | 58.7 | 17.0 | 39.5 | 0.0 | — |