← All comparisons
Mercury 2 vs Claude 4.1 Opus (Non-reasoning)
Inception vs Anthropic — side-by-side benchmark comparison
| Mercury 2 | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 32.8 | 36.0 |
| Coding Index | 30.6 | — |
| Math Index | — | — |
| Output speed (tok/s) | 983.1 | 44.7 |
| Blended price ($/1M) | $0.38 | $32.81 |
| Time to first token (s) | 3.48s | 1.63s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 30.60 | — |
| artificial analysis intelligence index | 32.80 | 36.00 |
| artificial analysis math index | — | — |
| gpqa | 77.0% | — |
| hle | 15.5% | — |
| ifbench | 69.8% | — |
| lcr | 36.3% | — |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 38.7% | — |
| tau2 | 70.8% | — |
| terminalbench hard | 26.5% | — |
Benchmark data from Artificial Analysis.