← All comparisons
GPT-5.2 (medium) vs Claude 4.1 Opus (Reasoning)
OpenAI vs Anthropic — side-by-side benchmark comparison
| GPT-5.2 (medium) | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 46.6 | 42.0 |
| Coding Index | 44.2 | 36.5 |
| Math Index | 96.7 | 80.3 |
| Output speed (tok/s) | 0.0 | 44.5 |
| Blended price ($/1M) | $4.81 | $32.81 |
| Time to first token (s) | 0.00s | 8.55s |
| aime | — | — |
| aime 25 | 96.7% | 80.3% |
| artificial analysis coding index | 44.20 | 36.50 |
| artificial analysis intelligence index | 46.60 | 42.00 |
| artificial analysis math index | 96.70 | 80.30 |
| gpqa | 86.4% | 80.9% |
| hle | 24.9% | 11.9% |
| ifbench | 65.2% | 55.4% |
| lcr | 63.3% | 66.3% |
| livecodebench | 89.4% | 65.4% |
| math 500 | — | — |
| mmlu pro | 85.9% | 88.0% |
| scicode | 46.2% | 40.9% |
| tau2 | 74.3% | 71.4% |
| terminalbench hard | 43.2% | 34.3% |
Benchmark data from Artificial Analysis.