← All comparisons
Cogito v2.1 (Reasoning) vs Claude 3.5 Sonnet (Oct '24)
Deep Cogito vs Anthropic — side-by-side benchmark comparison
| Cogito v2.1 (Reasoning) | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | — | 15.9 |
| Coding Index | 24.8 | 30.2 |
| Math Index | 72.7 | — |
| Output speed (tok/s) | 80.7 | 0.0 |
| Blended price ($/1M) | $1.25 | $6.56 |
| Time to first token (s) | 0.51s | 0.00s |
| aime | — | 15.7% |
| aime 25 | 72.7% | — |
| artificial analysis coding index | 24.80 | 30.20 |
| artificial analysis intelligence index | — | 15.90 |
| artificial analysis math index | 72.70 | — |
| gpqa | 76.8% | 59.9% |
| hle | 11.0% | 3.9% |
| ifbench | 46.3% | — |
| lcr | 21.7% | — |
| livecodebench | 68.8% | 38.1% |
| math 500 | — | 77.1% |
| mmlu pro | 84.9% | 77.2% |
| scicode | 41.0% | 36.6% |
| tau2 | — | — |
| terminalbench hard | 16.7% | — |
Benchmark data from Artificial Analysis.