← All comparisons
GPT-4.1 nano vs Claude 4.1 Opus (Reasoning)
OpenAI vs Anthropic — side-by-side benchmark comparison
| GPT-4.1 nano | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 13.0 | 42.0 |
| Coding Index | 11.2 | 36.5 |
| Math Index | 24.0 | 80.3 |
| Output speed (tok/s) | 178.9 | 44.5 |
| Blended price ($/1M) | $0.17 | $32.81 |
| Time to first token (s) | 0.40s | 8.55s |
| aime | 23.7% | — |
| aime 25 | 24.0% | 80.3% |
| artificial analysis coding index | 11.20 | 36.50 |
| artificial analysis intelligence index | 13.00 | 42.00 |
| artificial analysis math index | 24.00 | 80.30 |
| gpqa | 51.2% | 80.9% |
| hle | 3.9% | 11.9% |
| ifbench | 32.0% | 55.4% |
| lcr | 17.0% | 66.3% |
| livecodebench | 32.6% | 65.4% |
| math 500 | 84.8% | — |
| mmlu pro | 65.7% | 88.0% |
| scicode | 25.9% | 40.9% |
| tau2 | 17.3% | 71.4% |
| terminalbench hard | 3.8% | 34.3% |
Benchmark data from Artificial Analysis.