← All comparisons
Apriel-v1.5-15B-Thinker vs Qwen3 30B A3B 2507 Instruct
ServiceNow vs Alibaba — side-by-side benchmark comparison
| Apriel-v1.5-15B-Thinker | Qwen3 30B A3B 2507 Instruct | |
|---|---|---|
| Intelligence Index | 28.3 | 15.0 |
| Coding Index | 18.7 | 14.2 |
| Math Index | 87.5 | 66.3 |
| Output speed (tok/s) | 0.0 | 102.1 |
| Blended price ($/1M) | $0.00 | $0.21 |
| Time to first token (s) | 0.00s | 0.98s |
| aime | — | 72.7% |
| aime 25 | 87.5% | 66.3% |
| artificial analysis coding index | 18.70 | 14.20 |
| artificial analysis intelligence index | 28.30 | 15.00 |
| artificial analysis math index | 87.50 | 66.30 |
| gpqa | 71.3% | 65.9% |
| hle | 12.0% | 6.8% |
| ifbench | 61.7% | 33.1% |
| lcr | 20.0% | 22.7% |
| livecodebench | 72.8% | 51.5% |
| math 500 | — | 97.5% |
| mmlu pro | 77.3% | 77.7% |
| scicode | 34.8% | 30.4% |
| tau2 | 68.4% | 10.2% |
| terminalbench hard | 10.6% | 6.1% |
Benchmark data from Artificial Analysis.