← All comparisons
Phi-4 vs Olmo 3.1 32B Instruct
Microsoft vs Allen Institute for AI — side-by-side benchmark comparison
| Phi-4 | Olmo 3.1 32B Instruct | |
|---|---|---|
| Intelligence Index | 10.4 | 12.2 |
| Coding Index | 11.2 | 5.6 |
| Math Index | 18.0 | — |
| Output speed (tok/s) | 41.1 | 0.0 |
| Blended price ($/1M) | $0.22 | $0.00 |
| Time to first token (s) | 0.50s | 0.00s |
| aime | 14.3% | — |
| aime 25 | 18.0% | — |
| artificial analysis coding index | 11.20 | 5.60 |
| artificial analysis intelligence index | 10.40 | 12.20 |
| artificial analysis math index | 18.00 | — |
| gpqa | 57.5% | 53.9% |
| hle | 4.1% | 4.9% |
| ifbench | 23.5% | 39.2% |
| lcr | 0.0% | 0.0% |
| livecodebench | 23.1% | — |
| math 500 | 81.0% | — |
| mmlu pro | 71.4% | — |
| scicode | 26.0% | 16.7% |
| tau2 | 0.0% | 21.3% |
| terminalbench hard | 3.8% | 0.0% |
Benchmark data from Artificial Analysis.