← All comparisons
Apriel-v1.6-15B-Thinker vs GPT-4o (Aug '24)
ServiceNow vs OpenAI — side-by-side benchmark comparison
| Apriel-v1.6-15B-Thinker | GPT-4o (Aug '24) | |
|---|---|---|
| Intelligence Index | 27.6 | 18.6 |
| Coding Index | 22.0 | 16.6 |
| Math Index | 88.0 | — |
| Output speed (tok/s) | 0.0 | 117.5 |
| Blended price ($/1M) | $0.00 | $4.38 |
| Time to first token (s) | 0.00s | 0.60s |
| aime | — | 11.7% |
| aime 25 | 88.0% | — |
| artificial analysis coding index | 22.00 | 16.60 |
| artificial analysis intelligence index | 27.60 | 18.60 |
| artificial analysis math index | 88.00 | — |
| gpqa | 73.3% | 52.1% |
| hle | 9.8% | 2.9% |
| ifbench | 69.1% | 36.0% |
| lcr | 50.3% | 35.0% |
| livecodebench | 80.7% | 31.7% |
| math 500 | — | 79.5% |
| mmlu pro | 79.0% | — |
| scicode | 37.3% | 33.1% |
| tau2 | 69.3% | 28.9% |
| terminalbench hard | 14.4% | 8.3% |
Benchmark data from Artificial Analysis.