← All comparisons
Trinity Large Thinking vs Claude 4.1 Opus (Non-reasoning)
Arcee AI vs Anthropic — side-by-side benchmark comparison
| Trinity Large Thinking | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 31.9 | 36.0 |
| Coding Index | 27.2 | — |
| Math Index | — | — |
| Output speed (tok/s) | 171.4 | 44.7 |
| Blended price ($/1M) | $0.40 | $32.81 |
| Time to first token (s) | 0.67s | 1.63s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 27.20 | — |
| artificial analysis intelligence index | 31.90 | 36.00 |
| artificial analysis math index | — | — |
| gpqa | 75.2% | — |
| hle | 14.7% | — |
| ifbench | 56.3% | — |
| lcr | 33.0% | — |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 36.1% | — |
| tau2 | 90.1% | — |
| terminalbench hard | 22.7% | — |
Benchmark data from Artificial Analysis.