← All comparisons
Qwen3 Omni 30B A3B Instruct vs Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
Alibaba vs Google — side-by-side benchmark comparison
| Qwen3 Omni 30B A3B Instruct | Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) | |
|---|---|---|
| Intelligence Index | 10.7 | 21.6 |
| Coding Index | 7.2 | 18.2 |
| Math Index | 52.3 | 68.7 |
| Output speed (tok/s) | 108.9 | 0.0 |
| Blended price ($/1M) | $0.43 | $0.17 |
| Time to first token (s) | 1.04s | 0.00s |
| aime | — | — |
| aime 25 | 52.3% | 68.7% |
| artificial analysis coding index | 7.20 | 18.20 |
| artificial analysis intelligence index | 10.70 | 21.60 |
| artificial analysis math index | 52.30 | 68.70 |
| gpqa | 62.0% | 70.9% |
| hle | 5.1% | 6.6% |
| ifbench | 31.2% | 52.6% |
| lcr | 0.0% | 59.0% |
| livecodebench | 42.2% | 68.8% |
| math 500 | — | — |
| mmlu pro | 72.5% | 80.8% |
| scicode | 18.6% | 28.7% |
| tau2 | 16.4% | 30.7% |
| terminalbench hard | 1.5% | 12.9% |
Benchmark data from Artificial Analysis.