← All comparisons
GPT-5 nano (minimal) vs Claude 3.5 Sonnet (Oct '24)
OpenAI vs Anthropic — side-by-side benchmark comparison
| GPT-5 nano (minimal) | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | 13.8 | 15.9 |
| Coding Index | 14.2 | 30.2 |
| Math Index | 27.3 | — |
| Output speed (tok/s) | 175.6 | 0.0 |
| Blended price ($/1M) | $0.14 | $6.56 |
| Time to first token (s) | 0.67s | 0.00s |
| aime | — | 15.7% |
| aime 25 | 27.3% | — |
| artificial analysis coding index | 14.20 | 30.20 |
| artificial analysis intelligence index | 13.80 | 15.90 |
| artificial analysis math index | 27.30 | — |
| gpqa | 42.8% | 59.9% |
| hle | 4.1% | 3.9% |
| ifbench | 32.5% | — |
| lcr | 20.0% | — |
| livecodebench | 47.0% | 38.1% |
| math 500 | — | 77.1% |
| mmlu pro | 55.6% | 77.2% |
| scicode | 29.1% | 36.6% |
| tau2 | 25.7% | — |
| terminalbench hard | 6.8% | — |
Benchmark data from Artificial Analysis.