← All comparisons
Llama 4 Maverick vs Claude 4.5 Haiku (Reasoning)
Meta vs Anthropic — side-by-side benchmark comparison
| Llama 4 Maverick | Claude 4.5 Haiku (Reasoning) | |
|---|---|---|
| Intelligence Index | 18.4 | 37.1 |
| Coding Index | 15.6 | 32.6 |
| Math Index | 19.3 | 83.7 |
| Output speed (tok/s) | 119.7 | 142.2 |
| Blended price ($/1M) | $0.47 | $2.19 |
| Time to first token (s) | 0.64s | 10.48s |
| aime | 39.0% | — |
| aime 25 | 19.3% | 83.7% |
| artificial analysis coding index | 15.60 | 32.60 |
| artificial analysis intelligence index | 18.40 | 37.10 |
| artificial analysis math index | 19.30 | 83.70 |
| gpqa | 67.1% | 67.2% |
| hle | 4.8% | 9.7% |
| ifbench | 43.0% | 54.3% |
| lcr | 46.0% | 70.3% |
| livecodebench | 39.7% | 61.5% |
| math 500 | 88.9% | — |
| mmlu pro | 80.9% | 76.0% |
| scicode | 33.1% | 43.3% |
| tau2 | 17.8% | 54.7% |
| terminalbench hard | 6.8% | 27.3% |
Benchmark data from Artificial Analysis.