← All comparisons
Jamba 1.5 Large vs Qwen3 VL 32B Instruct
AI21 Labs vs Alibaba — side-by-side benchmark comparison
| Jamba 1.5 Large | Qwen3 VL 32B Instruct | |
|---|---|---|
| Intelligence Index | 10.7 | 17.2 |
| Coding Index | — | 15.6 |
| Math Index | — | 68.3 |
| Output speed (tok/s) | 0.0 | 76.1 |
| Blended price ($/1M) | $3.50 | $1.23 |
| Time to first token (s) | 0.00s | 1.30s |
| aime | 4.7% | — |
| aime 25 | — | 68.3% |
| artificial analysis coding index | — | 15.60 |
| artificial analysis intelligence index | 10.70 | 17.20 |
| artificial analysis math index | — | 68.30 |
| gpqa | 42.7% | 67.1% |
| hle | 4.0% | 6.3% |
| ifbench | — | 39.2% |
| lcr | — | 31.3% |
| livecodebench | 14.3% | 51.4% |
| math 500 | 60.6% | — |
| mmlu pro | 57.2% | 79.1% |
| scicode | 16.3% | 30.1% |
| tau2 | — | 29.2% |
| terminalbench hard | — | 8.3% |
Benchmark data from Artificial Analysis.