← All comparisons
GPT-4o mini vs Claude 3.5 Sonnet (Oct '24)
OpenAI vs Anthropic — side-by-side benchmark comparison
| GPT-4o mini | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | 12.6 | 15.9 |
| Coding Index | — | 30.2 |
| Math Index | 14.7 | — |
| Output speed (tok/s) | 69.6 | 0.0 |
| Blended price ($/1M) | $0.26 | $6.56 |
| Time to first token (s) | 0.62s | 0.00s |
| aime | 11.7% | 15.7% |
| aime 25 | 14.7% | — |
| artificial analysis coding index | — | 30.20 |
| artificial analysis intelligence index | 12.60 | 15.90 |
| artificial analysis math index | 14.70 | — |
| gpqa | 42.6% | 59.9% |
| hle | 4.0% | 3.9% |
| ifbench | 31.0% | — |
| lcr | — | — |
| livecodebench | 23.4% | 38.1% |
| math 500 | 78.9% | 77.1% |
| mmlu pro | 64.8% | 77.2% |
| scicode | 22.9% | 36.6% |
| tau2 | — | — |
| terminalbench hard | — | — |
Benchmark data from Artificial Analysis.