← All comparisons
Apriel-v1.6-15B-Thinker vs Claude 4.1 Opus (Non-reasoning)
ServiceNow vs Anthropic — side-by-side benchmark comparison
| Apriel-v1.6-15B-Thinker | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 27.6 | 36.0 |
| Coding Index | 22.0 | — |
| Math Index | 88.0 | — |
| Output speed (tok/s) | 0.0 | 44.7 |
| Blended price ($/1M) | $0.00 | $32.81 |
| Time to first token (s) | 0.00s | 1.63s |
| aime | — | — |
| aime 25 | 88.0% | — |
| artificial analysis coding index | 22.00 | — |
| artificial analysis intelligence index | 27.60 | 36.00 |
| artificial analysis math index | 88.00 | — |
| gpqa | 73.3% | — |
| hle | 9.8% | — |
| ifbench | 69.1% | — |
| lcr | 50.3% | — |
| livecodebench | 80.7% | — |
| math 500 | — | — |
| mmlu pro | 79.0% | — |
| scicode | 37.3% | — |
| tau2 | 69.3% | — |
| terminalbench hard | 14.4% | — |
Benchmark data from Artificial Analysis.