← All comparisons
Claude 4.1 Opus (Non-reasoning) vs GLM-4.7-Flash (Reasoning)
Anthropic vs Z AI — side-by-side benchmark comparison
| Claude 4.1 Opus (Non-reasoning) | GLM-4.7-Flash (Reasoning) | |
|---|---|---|
| Intelligence Index | 36.0 | 30.1 |
| Coding Index | — | 25.9 |
| Math Index | — | — |
| Output speed (tok/s) | 44.7 | 86.2 |
| Blended price ($/1M) | $32.81 | $0.15 |
| Time to first token (s) | 1.63s | 0.92s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | — | 25.90 |
| artificial analysis intelligence index | 36.00 | 30.10 |
| artificial analysis math index | — | — |
| gpqa | — | 58.1% |
| hle | — | 7.1% |
| ifbench | — | 60.8% |
| lcr | — | 35.0% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | — | 33.7% |
| tau2 | — | 98.8% |
| terminalbench hard | — | 22.0% |
Benchmark data from Artificial Analysis.