← All comparisons
Apriel-v1.6-15B-Thinker vs Qwen3 Omni 30B A3B (Reasoning)
ServiceNow vs Alibaba — side-by-side benchmark comparison
| Apriel-v1.6-15B-Thinker | Qwen3 Omni 30B A3B (Reasoning) | |
|---|---|---|
| Intelligence Index | 27.6 | 15.6 |
| Coding Index | 22.0 | 12.7 |
| Math Index | 88.0 | 74.0 |
| Output speed (tok/s) | 0.0 | 100.1 |
| Blended price ($/1M) | $0.00 | $0.43 |
| Time to first token (s) | 0.00s | 0.97s |
| aime | — | — |
| aime 25 | 88.0% | 74.0% |
| artificial analysis coding index | 22.00 | 12.70 |
| artificial analysis intelligence index | 27.60 | 15.60 |
| artificial analysis math index | 88.00 | 74.00 |
| gpqa | 73.3% | 72.6% |
| hle | 9.8% | 7.3% |
| ifbench | 69.1% | 43.4% |
| lcr | 50.3% | 0.0% |
| livecodebench | 80.7% | 67.9% |
| math 500 | — | — |
| mmlu pro | 79.0% | 79.2% |
| scicode | 37.3% | 30.6% |
| tau2 | 69.3% | 21.3% |
| terminalbench hard | 14.4% | 3.8% |
Benchmark data from Artificial Analysis.