← All comparisons
Jamba Reasoning 3B vs Qwen3 30B A3B (Reasoning)
AI21 Labs vs Alibaba — side-by-side benchmark comparison
| Jamba Reasoning 3B | Qwen3 30B A3B (Reasoning) | |
|---|---|---|
| Intelligence Index | 9.6 | 15.3 |
| Coding Index | 2.5 | 11.0 |
| Math Index | 10.7 | 72.3 |
| Output speed (tok/s) | 0.0 | 64.1 |
| Blended price ($/1M) | $0.00 | $0.18 |
| Time to first token (s) | 0.00s | 1.18s |
| aime | — | 75.3% |
| aime 25 | 10.7% | 72.3% |
| artificial analysis coding index | 2.50 | 11.00 |
| artificial analysis intelligence index | 9.60 | 15.30 |
| artificial analysis math index | 10.70 | 72.30 |
| gpqa | 33.3% | 61.6% |
| hle | 4.6% | 6.6% |
| ifbench | 52.4% | 41.5% |
| lcr | 7.0% | 0.0% |
| livecodebench | 21.0% | 50.6% |
| math 500 | — | 95.9% |
| mmlu pro | 57.7% | 77.7% |
| scicode | 5.9% | 28.5% |
| tau2 | 15.8% | 26.0% |
| terminalbench hard | 0.8% | 2.3% |
Benchmark data from Artificial Analysis.