← All comparisons
Claude 4.1 Opus (Non-reasoning) vs GLM-5 (Non-reasoning)
Anthropic vs Z AI — side-by-side benchmark comparison
| Claude 4.1 Opus (Non-reasoning) | GLM-5 (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 36.0 | 40.6 |
| Coding Index | — | 39.0 |
| Math Index | — | — |
| Output speed (tok/s) | 44.7 | 66.0 |
| Blended price ($/1M) | $32.81 | $1.55 |
| Time to first token (s) | 1.63s | 1.17s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | — | 39.00 |
| artificial analysis intelligence index | 36.00 | 40.60 |
| artificial analysis math index | — | — |
| gpqa | — | 66.6% |
| hle | — | 7.2% |
| ifbench | — | 55.2% |
| lcr | — | 37.0% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | — | 38.3% |
| tau2 | — | 97.4% |
| terminalbench hard | — | 39.4% |
Benchmark data from Artificial Analysis.