← All comparisons
Qwen3.5 122B A10B (Non-reasoning) vs Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
Alibaba vs Google — side-by-side benchmark comparison
| Qwen3.5 122B A10B (Non-reasoning) | Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) | |
|---|---|---|
| Intelligence Index | 35.9 | 21.6 |
| Coding Index | 31.6 | 18.2 |
| Math Index | — | 68.7 |
| Output speed (tok/s) | 165.9 | 0.0 |
| Blended price ($/1M) | $1.10 | $0.17 |
| Time to first token (s) | 1.06s | 0.00s |
| aime | — | — |
| aime 25 | — | 68.7% |
| artificial analysis coding index | 31.60 | 18.20 |
| artificial analysis intelligence index | 35.90 | 21.60 |
| artificial analysis math index | — | 68.70 |
| gpqa | 82.7% | 70.9% |
| hle | 14.8% | 6.6% |
| ifbench | 50.8% | 52.6% |
| lcr | 56.0% | 59.0% |
| livecodebench | — | 68.8% |
| math 500 | — | — |
| mmlu pro | — | 80.8% |
| scicode | 35.6% | 28.7% |
| tau2 | 84.5% | 30.7% |
| terminalbench hard | 29.5% | 12.9% |
Benchmark data from Artificial Analysis.