← All comparisons
o3 vs Claude 4.1 Opus (Reasoning)
OpenAI vs Anthropic — side-by-side benchmark comparison
| o3 | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 38.4 | 42.0 |
| Coding Index | 38.4 | 36.5 |
| Math Index | 88.3 | 80.3 |
| Output speed (tok/s) | 126.8 | 44.5 |
| Blended price ($/1M) | $3.50 | $32.81 |
| Time to first token (s) | 7.82s | 8.55s |
| aime | 90.3% | — |
| aime 25 | 88.3% | 80.3% |
| artificial analysis coding index | 38.40 | 36.50 |
| artificial analysis intelligence index | 38.40 | 42.00 |
| artificial analysis math index | 88.30 | 80.30 |
| gpqa | 82.7% | 80.9% |
| hle | 20.0% | 11.9% |
| ifbench | 71.4% | 55.4% |
| lcr | 69.3% | 66.3% |
| livecodebench | 80.8% | 65.4% |
| math 500 | 99.2% | — |
| mmlu pro | 85.3% | 88.0% |
| scicode | 41.0% | 40.9% |
| tau2 | 80.7% | 71.4% |
| terminalbench hard | 37.1% | 34.3% |
Benchmark data from Artificial Analysis.