Calibration
AA-HLE → Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index is estimated from AA-HLE with a offset logistic curve fitted on 166 models measured on both: y = 0.0702 + (0.7333 − 0.0702) / (1 + exp(−7.39·(x − 0.4589))), R² = 0.81, cross-validated error 7.5 pp. It is used for 23 estimates.
| Estimated model | AA-HLE | Artificial Analysis Intelligence Index | Source |
|---|---|---|---|
| GPT-5.3 Codex | 42.5% | 36.0% | estimated ± 7.5 pp, medium confidence |
| Ling 3.1 Flash | 39.4% | 32.4% | estimated ± 7.5 pp, medium confidence |
| Kimi K2.7 Code | 35.0% | 27.5% | estimated ± 7.5 pp, medium confidence |
| Hy3 | 33.5% | 26.0% | estimated ± 7.5 pp, medium confidence |
| Ling 3.0 Flash VL | 22.0% | 16.7% | estimated ± 7.5 pp, medium confidence |
| Quasar 438B | 18.7% | 14.9% | estimated ± 7.5 pp, medium confidence |
| Trinity-Large-Thinking | 15.8% | 13.5% | estimated ± 7.5 pp, medium confidence |
| Mercury 2.5 | 11.8% | 12.0% | estimated ± 7.5 pp, medium confidence |
| Qwen3.5-4B | 9.9% | 11.4% | estimated ± 7.5 pp, medium confidence |
| Ling 3.0 Tiny | 9.3% | 11.2% | estimated ± 7.5 pp, medium confidence |
| Qwen3-Omni-30B-A3B-Thinking | 7.5% | 10.7% | estimated ± 7.5 pp, medium confidence |
| LFM2.5-8B-A1B | 6.9% | 10.5% | estimated ± 7.5 pp, medium confidence |
| Celeris-1 | 6.8% | 10.5% | estimated ± 7.5 pp, medium confidence |
| LFM2.5-2.6B | 6.2% | 10.4% | estimated ± 7.5 pp, medium confidence |
| Exaone 4.0 1.2B | 5.7% | 10.3% | estimated ± 7.5 pp, medium confidence |
| LFM2.5-VL-1.6B-Extract | 5.1% | 10.1% | estimated ± 7.5 pp, medium confidence |
| Exaone 4.0 32B | 5.0% | 10.1% | estimated ± 7.5 pp, medium confidence |
| Phi-4 Multimodal Instruct | 5.0% | 10.1% | estimated ± 7.5 pp, medium confidence |
| Llama 4 Maverick | 4.9% | 10.1% | estimated ± 7.5 pp, medium confidence |
| Qwen3-Omni-30B-A3B-Instruct | 4.6% | 10.0% | estimated ± 7.5 pp, medium confidence |
| Llama 3.1 405B | 4.0% | 9.9% | estimated ± 7.5 pp, medium confidence |
| Llama 4 Scout | 3.8% | 9.8% | estimated ± 7.5 pp, medium confidence |
| Ultravox v0.6 Llama 3.3 70B | 3.6% | 9.8% | estimated ± 7.5 pp, medium confidence |