← All comparisons
gpt-oss-20B (low) vs Claude 4.1 Opus (Non-reasoning)
OpenAI vs Anthropic — side-by-side benchmark comparison
| gpt-oss-20B (low) | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 20.8 | 36.0 |
| Coding Index | 14.4 | — |
| Math Index | 62.3 | — |
| Output speed (tok/s) | 273.0 | 44.7 |
| Blended price ($/1M) | $0.10 | $32.81 |
| Time to first token (s) | 0.50s | 1.63s |
| aime | — | — |
| aime 25 | 62.3% | — |
| artificial analysis coding index | 14.40 | — |
| artificial analysis intelligence index | 20.80 | 36.00 |
| artificial analysis math index | 62.30 | — |
| gpqa | 61.1% | — |
| hle | 5.1% | — |
| ifbench | 57.8% | — |
| lcr | 31.0% | — |
| livecodebench | 65.2% | — |
| math 500 | — | — |
| mmlu pro | 71.8% | — |
| scicode | 34.0% | — |
| tau2 | 50.3% | — |
| terminalbench hard | 4.5% | — |
Benchmark data from Artificial Analysis.