← All comparisons
GPT-5.4 nano (Non-Reasoning) vs Jamba 1.6 Large
OpenAI vs AI21 Labs — side-by-side benchmark comparison
| GPT-5.4 nano (Non-Reasoning) | Jamba 1.6 Large | |
|---|---|---|
| Intelligence Index | 24.4 | 10.6 |
| Coding Index | 27.9 | — |
| Math Index | — | — |
| Output speed (tok/s) | 157.4 | 54.9 |
| Blended price ($/1M) | $0.46 | $3.50 |
| Time to first token (s) | 0.54s | 0.87s |
| aime | — | 4.7% |
| aime 25 | — | — |
| artificial analysis coding index | 27.90 | — |
| artificial analysis intelligence index | 24.40 | 10.60 |
| artificial analysis math index | — | — |
| gpqa | 55.8% | 38.7% |
| hle | 4.2% | 4.0% |
| ifbench | 32.7% | — |
| lcr | 24.7% | — |
| livecodebench | — | 17.2% |
| math 500 | — | 58.0% |
| mmlu pro | — | 56.5% |
| scicode | 35.2% | 18.4% |
| tau2 | 34.8% | — |
| terminalbench hard | 24.2% | — |
Benchmark data from Artificial Analysis.