← All comparisons
gpt-oss-120b (low) vs Claude 4.1 Opus (Non-reasoning)
OpenAI vs Anthropic — side-by-side benchmark comparison
| gpt-oss-120b (low) | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 24.5 | 36.0 |
| Coding Index | 15.5 | — |
| Math Index | 66.7 | — |
| Output speed (tok/s) | 370.0 | 44.7 |
| Blended price ($/1M) | $0.26 | $32.81 |
| Time to first token (s) | 0.49s | 1.63s |
| aime | — | — |
| aime 25 | 66.7% | — |
| artificial analysis coding index | 15.50 | — |
| artificial analysis intelligence index | 24.50 | 36.00 |
| artificial analysis math index | 66.70 | — |
| gpqa | 67.2% | — |
| hle | 5.2% | — |
| ifbench | 58.3% | — |
| lcr | 43.7% | — |
| livecodebench | 70.7% | — |
| math 500 | — | — |
| mmlu pro | 77.5% | — |
| scicode | 36.0% | — |
| tau2 | 45.0% | — |
| terminalbench hard | 5.3% | — |
Benchmark data from Artificial Analysis.