← All comparisons
Ling-2.6-1T vs GPT-5.1 Codex (high)
InclusionAI vs OpenAI — side-by-side benchmark comparison
| Ling-2.6-1T | GPT-5.1 Codex (high) | |
|---|---|---|
| Intelligence Index | 33.6 | 43.1 |
| Coding Index | 33.1 | 36.6 |
| Math Index | — | 95.7 |
| Output speed (tok/s) | 0.0 | 182.1 |
| Blended price ($/1M) | $0.85 | $3.44 |
| Time to first token (s) | 0.00s | 5.42s |
| aime | — | — |
| aime 25 | — | 95.7% |
| artificial analysis coding index | 33.10 | 36.60 |
| artificial analysis intelligence index | 33.60 | 43.10 |
| artificial analysis math index | — | 95.70 |
| gpqa | 75.2% | 86.0% |
| hle | 8.2% | 23.4% |
| ifbench | 56.9% | 70.0% |
| lcr | 34.7% | 67.3% |
| livecodebench | — | 84.9% |
| math 500 | — | — |
| mmlu pro | — | 86.0% |
| scicode | 37.0% | 40.2% |
| tau2 | 89.8% | 83.0% |
| terminalbench hard | 31.1% | 34.8% |
Benchmark data from Artificial Analysis.