← All comparisons
Gemini 3 Flash Preview (Reasoning) vs Llama 3.1 Tulu3 405B
Google vs Allen Institute for AI — side-by-side benchmark comparison
| Gemini 3 Flash Preview (Reasoning) | Llama 3.1 Tulu3 405B | |
|---|---|---|
| Intelligence Index | 46.4 | 14.1 |
| Coding Index | 42.6 | — |
| Math Index | 97.0 | — |
| Output speed (tok/s) | 192.1 | 0.0 |
| Blended price ($/1M) | $1.13 | $0.00 |
| Time to first token (s) | 6.35s | 0.00s |
| aime | — | 13.3% |
| aime 25 | 97.0% | — |
| artificial analysis coding index | 42.60 | — |
| artificial analysis intelligence index | 46.40 | 14.10 |
| artificial analysis math index | 97.00 | — |
| gpqa | 89.8% | 51.6% |
| hle | 34.7% | 3.5% |
| ifbench | 78.0% | — |
| lcr | 66.3% | — |
| livecodebench | 90.8% | 29.1% |
| math 500 | — | 77.8% |
| mmlu pro | 89.0% | 71.6% |
| scicode | 50.6% | 30.2% |
| tau2 | 80.4% | — |
| terminalbench hard | 38.6% | — |
Benchmark data from Artificial Analysis.