← All comparisons
gpt-oss-120b (high) vs Claude 4.1 Opus (Non-reasoning)
OpenAI vs Anthropic — side-by-side benchmark comparison
| gpt-oss-120b (high) | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 33.3 | 36.0 |
| Coding Index | 28.6 | — |
| Math Index | 93.4 | — |
| Output speed (tok/s) | 356.8 | 44.7 |
| Blended price ($/1M) | $0.26 | $32.81 |
| Time to first token (s) | 0.51s | 1.63s |
| aime | — | — |
| aime 25 | 93.4% | — |
| artificial analysis coding index | 28.60 | — |
| artificial analysis intelligence index | 33.30 | 36.00 |
| artificial analysis math index | 93.40 | — |
| gpqa | 78.2% | — |
| hle | 18.5% | — |
| ifbench | 69.0% | — |
| lcr | 50.7% | — |
| livecodebench | 87.8% | — |
| math 500 | — | — |
| mmlu pro | 80.8% | — |
| scicode | 38.9% | — |
| tau2 | 65.8% | — |
| terminalbench hard | 23.5% | — |
Benchmark data from Artificial Analysis.