← All comparisons
DeepSeek R1 Distill Llama 8B vs Ling-1T
DeepSeek vs InclusionAI — side-by-side benchmark comparison
| DeepSeek R1 Distill Llama 8B | Ling-1T | |
|---|---|---|
| Intelligence Index | 12.1 | 19.0 |
| Coding Index | — | 18.8 |
| Math Index | 41.3 | 71.3 |
| 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 | 33.3% | — |
| aime 25 | 41.3% | 71.3% |
| artificial analysis coding index | — | 18.80 |
| artificial analysis intelligence index | 12.10 | 19.00 |
| artificial analysis math index | 41.30 | 71.30 |
| gpqa | 30.2% | 71.9% |
| hle | 4.2% | 7.2% |
| ifbench | 17.6% | 34.8% |
| lcr | 0.0% | 34.7% |
| livecodebench | 23.3% | 67.7% |
| math 500 | 85.3% | — |
| mmlu pro | 54.3% | 82.2% |
| scicode | 11.9% | 35.2% |
| tau2 | — | 32.7% |
| terminalbench hard | — | 10.6% |
Benchmark data from Artificial Analysis.