← All comparisons
Claude 4.5 Haiku (Reasoning) vs Mercury 2
Anthropic vs Inception — side-by-side benchmark comparison
| Claude 4.5 Haiku (Reasoning) | Mercury 2 | |
|---|---|---|
| Intelligence Index | 37.1 | 32.8 |
| Coding Index | 32.6 | 30.6 |
| Math Index | 83.7 | — |
| Output speed (tok/s) | 142.2 | 983.1 |
| Blended price ($/1M) | $2.19 | $0.38 |
| Time to first token (s) | 10.48s | 3.48s |
| aime | — | — |
| aime 25 | 83.7% | — |
| artificial analysis coding index | 32.60 | 30.60 |
| artificial analysis intelligence index | 37.10 | 32.80 |
| artificial analysis math index | 83.70 | — |
| gpqa | 67.2% | 77.0% |
| hle | 9.7% | 15.5% |
| ifbench | 54.3% | 69.8% |
| lcr | 70.3% | 36.3% |
| livecodebench | 61.5% | — |
| math 500 | — | — |
| mmlu pro | 76.0% | — |
| scicode | 43.3% | 38.7% |
| tau2 | 54.7% | 70.8% |
| terminalbench hard | 27.3% | 26.5% |
Benchmark data from Artificial Analysis.