← All comparisons
Llama 3.2 Instruct 90B (Vision) vs Olmo 3 32B Think
Meta vs Allen Institute for AI — side-by-side benchmark comparison
| Llama 3.2 Instruct 90B (Vision) | Olmo 3 32B Think | |
|---|---|---|
| Intelligence Index | 11.9 | 12.1 |
| Coding Index | — | 10.5 |
| Math Index | — | 73.7 |
| Output speed (tok/s) | 47.1 | 0.0 |
| Blended price ($/1M) | $1.38 | $0.00 |
| Time to first token (s) | 0.48s | 0.00s |
| aime | 5.0% | — |
| aime 25 | — | 73.7% |
| artificial analysis coding index | — | 10.50 |
| artificial analysis intelligence index | 11.90 | 12.10 |
| artificial analysis math index | — | 73.70 |
| gpqa | 43.2% | 61.0% |
| hle | 4.9% | 5.9% |
| ifbench | — | 49.1% |
| lcr | — | 0.0% |
| livecodebench | 21.4% | 67.2% |
| math 500 | 62.9% | — |
| mmlu pro | 67.1% | 75.9% |
| scicode | 24.0% | 28.6% |
| tau2 | — | 0.0% |
| terminalbench hard | — | 1.5% |
Benchmark data from Artificial Analysis.