← All comparisons
Jamba Reasoning 3B vs DeepSeek R1 Distill Qwen 1.5B
AI21 Labs vs DeepSeek — side-by-side benchmark comparison
| Jamba Reasoning 3B | DeepSeek R1 Distill Qwen 1.5B | |
|---|---|---|
| Intelligence Index | 9.6 | 9.1 |
| Coding Index | 2.5 | — |
| Math Index | 10.7 | 22.0 |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.00 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | — | 17.7% |
| aime 25 | 10.7% | 22.0% |
| artificial analysis coding index | 2.50 | — |
| artificial analysis intelligence index | 9.60 | 9.10 |
| artificial analysis math index | 10.70 | 22.00 |
| gpqa | 33.3% | 9.8% |
| hle | 4.6% | 3.3% |
| ifbench | 52.4% | 13.2% |
| lcr | 7.0% | 0.3% |
| livecodebench | 21.0% | 7.0% |
| math 500 | — | 68.7% |
| mmlu pro | 57.7% | 26.9% |
| scicode | 5.9% | 6.6% |
| tau2 | 15.8% | — |
| terminalbench hard | 0.8% | — |
Benchmark data from Artificial Analysis.