← All comparisons
GPT-4.1 vs Claude 3.5 Sonnet (Oct '24)
OpenAI vs Anthropic — side-by-side benchmark comparison
| GPT-4.1 | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | 26.3 | 15.9 |
| Coding Index | 21.8 | 30.2 |
| Math Index | 34.7 | — |
| Output speed (tok/s) | 137.8 | 0.0 |
| Blended price ($/1M) | $3.50 | $6.56 |
| Time to first token (s) | 0.58s | 0.00s |
| aime | 43.7% | 15.7% |
| aime 25 | 34.7% | — |
| artificial analysis coding index | 21.80 | 30.20 |
| artificial analysis intelligence index | 26.30 | 15.90 |
| artificial analysis math index | 34.70 | — |
| gpqa | 66.6% | 59.9% |
| hle | 4.6% | 3.9% |
| ifbench | 43.0% | — |
| lcr | 61.0% | — |
| livecodebench | 45.7% | 38.1% |
| math 500 | 91.3% | 77.1% |
| mmlu pro | 80.6% | 77.2% |
| scicode | 38.1% | 36.6% |
| tau2 | 47.1% | — |
| terminalbench hard | 13.6% | — |
Benchmark data from Artificial Analysis.