← All comparisons
GPT-4.1 mini vs Claude 3.5 Sonnet (Oct '24)
OpenAI vs Anthropic — side-by-side benchmark comparison
| GPT-4.1 mini | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | 22.9 | 15.9 |
| Coding Index | 18.5 | 30.2 |
| Math Index | 46.3 | — |
| Output speed (tok/s) | 95.1 | 0.0 |
| Blended price ($/1M) | $0.70 | $6.56 |
| Time to first token (s) | 0.59s | 0.00s |
| aime | 43.0% | 15.7% |
| aime 25 | 46.3% | — |
| artificial analysis coding index | 18.50 | 30.20 |
| artificial analysis intelligence index | 22.90 | 15.90 |
| artificial analysis math index | 46.30 | — |
| gpqa | 66.4% | 59.9% |
| hle | 4.6% | 3.9% |
| ifbench | 38.3% | — |
| lcr | 42.3% | — |
| livecodebench | 48.3% | 38.1% |
| math 500 | 92.5% | 77.1% |
| mmlu pro | 78.1% | 77.2% |
| scicode | 40.4% | 36.6% |
| tau2 | 52.9% | — |
| terminalbench hard | 7.6% | — |
Benchmark data from Artificial Analysis.