← All comparisons
OLMo 2 32B vs GLM-4.5 (Reasoning)
Allen Institute for AI vs Z AI — side-by-side benchmark comparison
| OLMo 2 32B | GLM-4.5 (Reasoning) | |
|---|---|---|
| Intelligence Index | 10.6 | 26.4 |
| Coding Index | 2.7 | 26.3 |
| Math Index | 3.3 | 73.7 |
| Output speed (tok/s) | 0.0 | 53.3 |
| Blended price ($/1M) | $0.00 | $1.00 |
| Time to first token (s) | 0.00s | 1.19s |
| aime | — | 87.3% |
| aime 25 | 3.3% | 73.7% |
| artificial analysis coding index | 2.70 | 26.30 |
| artificial analysis intelligence index | 10.60 | 26.40 |
| artificial analysis math index | 3.30 | 73.70 |
| gpqa | 32.8% | 78.2% |
| hle | 3.7% | 12.2% |
| ifbench | 38.1% | 44.1% |
| lcr | 0.0% | 48.3% |
| livecodebench | 6.8% | 73.8% |
| math 500 | — | 97.9% |
| mmlu pro | 51.1% | 83.5% |
| scicode | 8.0% | 34.8% |
| tau2 | 0.0% | 43.0% |
| terminalbench hard | 0.0% | 22.0% |
Benchmark data from Artificial Analysis.