← All comparisons
Sonar Pro vs Qwen3 VL 30B A3B (Reasoning)
Perplexity vs Alibaba — side-by-side benchmark comparison
| Sonar Pro | Qwen3 VL 30B A3B (Reasoning) | |
|---|---|---|
| Intelligence Index | 15.2 | 19.7 |
| Coding Index | — | 13.1 |
| Math Index | — | 82.3 |
| Output speed (tok/s) | 0.0 | 123.6 |
| Blended price ($/1M) | $0.00 | $0.34 |
| Time to first token (s) | 0.00s | 1.09s |
| aime | 29.0% | — |
| aime 25 | — | 82.3% |
| artificial analysis coding index | — | 13.10 |
| artificial analysis intelligence index | 15.20 | 19.70 |
| artificial analysis math index | — | 82.30 |
| gpqa | 57.8% | 72.0% |
| hle | 7.9% | 8.7% |
| ifbench | — | 45.1% |
| lcr | — | 40.7% |
| livecodebench | 27.5% | 69.7% |
| math 500 | 74.5% | — |
| mmlu pro | 75.5% | 80.7% |
| scicode | 22.6% | 28.8% |
| tau2 | — | 19.9% |
| terminalbench hard | — | 5.3% |
Benchmark data from Artificial Analysis.