← All comparisons
Claude 3.5 Sonnet (June '24) vs GLM-4.6 (Non-reasoning)
Anthropic vs Z AI — side-by-side benchmark comparison
| Claude 3.5 Sonnet (June '24) | GLM-4.6 (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 14.2 | 30.2 |
| Coding Index | 26.0 | 30.2 |
| Math Index | — | 44.3 |
| Output speed (tok/s) | 0.0 | 53.2 |
| Blended price ($/1M) | $6.56 | $1.00 |
| Time to first token (s) | 0.00s | 1.84s |
| aime | 9.7% | — |
| aime 25 | — | 44.3% |
| artificial analysis coding index | 26.00 | 30.20 |
| artificial analysis intelligence index | 14.20 | 30.20 |
| artificial analysis math index | — | 44.30 |
| gpqa | 56.0% | 63.2% |
| hle | 3.7% | 5.2% |
| ifbench | — | 36.7% |
| lcr | — | 26.3% |
| livecodebench | — | 56.1% |
| math 500 | 69.5% | — |
| mmlu pro | 75.1% | 78.4% |
| scicode | 31.6% | 33.1% |
| tau2 | — | 76.9% |
| terminalbench hard | — | 28.8% |
Benchmark data from Artificial Analysis.