Artificial Analysis's composite Intelligence Index as reported in the LLM Benchmark Matrix. Aggregates multiple evals into a single capability score.
This definition has not completed editorial and provenance review. Verify its metric, version, source, and evaluation configuration upstream before using it for a model-selection decision.
Single-number summary of broad model capability. Useful for quick comparisons.
Composite methodology is proprietary to Artificial Analysis. This is the matrix snapshot — AA's own column may be fresher.
Higher is better. Typical range 51–73 for frontier models.
Composite methodology is proprietary to Artificial Analysis.
| # | Model | Score |
|---|---|---|
| 1 | 83.8 | |
| 2 | 83.2 | |
| 3 | 82.4 | |
| 4 | 80.0 | |
| 5 | 77.9 | |
| 6 | 75.3 | |
| 7 | 75.0 | |
| 8 | 74.6 | |
| 9 | 74.6 | |
| 10 | 74.3 | |
| 11 | 74.2 | |
| 12 | 73.5 | |
| 13 | 73.2 | |
| 14 | 73.2 | |
| 15 | 73.0 | |
| 16 | 72.9 | |
| 17 | 72.8 | |
| 18 | 72.7 | |
| 19 | 72.4 | |
| 20 | 72.4 | |
| 21 | 72.3 | |
| 22 | 72.3 | |
| 23 | 72.3 | |
| 24 | 72.2 | |
| 25 | 71.8 | |
| 26 | 71.8 | |
| 27 | 71.5 | |
| 28 | 71.4 | |
| 29 | 71.2 | |
| 30 | 71.1 | |
| 31 | 71.1 | |
| 32 | 71.0 | |
| 33 | 70.9 | |
| 34 | 70.9 | |
| 35 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) source benchpress Evidence observed Apr 13, 2026 | 70.7 |
| 36 | 70.6 | |
| 37 | 70.6 | |
| 38 | 70.5 | |
| 39 | 70.3 | |
| 40 | 70.3 | |
| 41 | 70.2 | |
| 42 | 70.1 | |
| 43 | 70.1 | |
| 44 | 70.0 | |
| 45 | 70.0 | |
| 46 | 70.0 | |
| 47 | 70.0 | |
| 48 | 69.9 | |
| 49 | 69.9 | |
| 50 | 69.8 |