← All comparisons
Qwen3.6 35B A3B (Non-reasoning) vs Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
Alibaba vs Anthropic — side-by-side benchmark comparison
| Qwen3.6 35B A3B (Non-reasoning) | Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | |
|---|---|---|
| Intelligence Index | 31.5 | 52.9 |
| Coding Index | 17.6 | 48.1 |
| Math Index | — | — |
| Output speed (tok/s) | 169.5 | 54.8 |
| Blended price ($/1M) | $0.84 | $10.94 |
| Time to first token (s) | 1.47s | 11.69s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 17.60 | 48.10 |
| artificial analysis intelligence index | 31.50 | 52.90 |
| artificial analysis math index | — | — |
| gpqa | 81.7% | 89.6% |
| hle | 12.5% | 36.7% |
| ifbench | 36.2% | 53.1% |
| lcr | 56.7% | 70.7% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 1.3% | 51.9% |
| tau2 | 85.1% | 92.1% |
| terminalbench hard | 25.8% | 46.2% |
Benchmark data from Artificial Analysis.