← All comparisons
Claude 4.5 Haiku (Reasoning) vs Cogito v2.1 (Reasoning)
Anthropic vs Deep Cogito — side-by-side benchmark comparison
| Claude 4.5 Haiku (Reasoning) | Cogito v2.1 (Reasoning) | |
|---|---|---|
| Intelligence Index | 37.1 | — |
| Coding Index | 32.6 | 24.8 |
| Math Index | 83.7 | 72.7 |
| Output speed (tok/s) | 142.2 | 80.7 |
| Blended price ($/1M) | $2.19 | $1.25 |
| Time to first token (s) | 10.48s | 0.51s |
| aime | — | — |
| aime 25 | 83.7% | 72.7% |
| artificial analysis coding index | 32.60 | 24.80 |
| artificial analysis intelligence index | 37.10 | — |
| artificial analysis math index | 83.70 | 72.70 |
| gpqa | 67.2% | 76.8% |
| hle | 9.7% | 11.0% |
| ifbench | 54.3% | 46.3% |
| lcr | 70.3% | 21.7% |
| livecodebench | 61.5% | 68.8% |
| math 500 | — | — |
| mmlu pro | 76.0% | 84.9% |
| scicode | 43.3% | 41.0% |
| tau2 | 54.7% | — |
| terminalbench hard | 27.3% | 16.7% |
Benchmark data from Artificial Analysis.