← All comparisons
GPT-4o (Nov '24) vs Claude 4.1 Opus (Reasoning)
OpenAI vs Anthropic — side-by-side benchmark comparison
| GPT-4o (Nov '24) | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 17.3 | 42.0 |
| Coding Index | 16.7 | 36.5 |
| Math Index | 6.0 | 80.3 |
| Output speed (tok/s) | 158.5 | 44.5 |
| Blended price ($/1M) | $4.38 | $32.81 |
| Time to first token (s) | 0.54s | 8.55s |
| aime | 15.0% | — |
| aime 25 | 6.0% | 80.3% |
| artificial analysis coding index | 16.70 | 36.50 |
| artificial analysis intelligence index | 17.30 | 42.00 |
| artificial analysis math index | 6.00 | 80.30 |
| gpqa | 54.3% | 80.9% |
| hle | 3.3% | 11.9% |
| ifbench | 34.3% | 55.4% |
| lcr | 0.0% | 66.3% |
| livecodebench | 30.9% | 65.4% |
| math 500 | 75.9% | — |
| mmlu pro | 74.8% | 88.0% |
| scicode | 33.3% | 40.9% |
| tau2 | 25.1% | 71.4% |
| terminalbench hard | 8.3% | 34.3% |
Benchmark data from Artificial Analysis.