← All comparisons
Llama 4 Scout vs Olmo 3 32B Think
Meta vs Allen Institute for AI — side-by-side benchmark comparison
| Llama 4 Scout | Olmo 3 32B Think | |
|---|---|---|
| Intelligence Index | 13.5 | 12.1 |
| Coding Index | 6.7 | 10.5 |
| Math Index | 14.0 | 73.7 |
| Output speed (tok/s) | 113.8 | 0.0 |
| Blended price ($/1M) | $0.29 | $0.00 |
| Time to first token (s) | 0.56s | 0.00s |
| aime | 28.3% | — |
| aime 25 | 14.0% | 73.7% |
| artificial analysis coding index | 6.70 | 10.50 |
| artificial analysis intelligence index | 13.50 | 12.10 |
| artificial analysis math index | 14.00 | 73.70 |
| gpqa | 58.7% | 61.0% |
| hle | 4.3% | 5.9% |
| ifbench | 39.5% | 49.1% |
| lcr | 25.8% | 0.0% |
| livecodebench | 29.9% | 67.2% |
| math 500 | 84.4% | — |
| mmlu pro | 75.2% | 75.9% |
| scicode | 17.0% | 28.6% |
| tau2 | 15.5% | 0.0% |
| terminalbench hard | 1.5% | 1.5% |
Benchmark data from Artificial Analysis.