← All comparisons
Jamba 1.7 Mini vs Qwen3.5 35B A3B (Non-reasoning)
AI21 Labs vs Alibaba — side-by-side benchmark comparison
| Jamba 1.7 Mini | Qwen3.5 35B A3B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 8.1 | 30.7 |
| Coding Index | 3.1 | 16.8 |
| Math Index | 0.3 | — |
| Output speed (tok/s) | 0.0 | 147.9 |
| Blended price ($/1M) | $0.00 | $0.69 |
| Time to first token (s) | 0.00s | 1.18s |
| aime | 1.3% | — |
| aime 25 | 0.3% | — |
| artificial analysis coding index | 3.10 | 16.80 |
| artificial analysis intelligence index | 8.10 | 30.70 |
| artificial analysis math index | 30.0% | — |
| gpqa | 32.2% | 81.9% |
| hle | 4.5% | 12.8% |
| ifbench | 31.4% | 44.5% |
| lcr | 12.7% | 55.3% |
| livecodebench | 6.1% | — |
| math 500 | 25.8% | — |
| mmlu pro | 38.8% | — |
| scicode | 9.3% | 29.3% |
| tau2 | 12.6% | 86.3% |
| terminalbench hard | 0.0% | 10.6% |
Benchmark data from Artificial Analysis.