Apriel-v1.5-15B-Thinker: benchmark results
Provider: ServiceNow. Released 2025-06-01.
Aggregate Rating 1574 ± 26, rank #1343 of 10916 rated models, from 43 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA AIME 2025 | 87.5 | Accuracy (%) | 84.5 |
| AA LiveCodeBench | 72.8 | Pass@1 (%) | 83.6 |
| AA IFBench | 61.7 | Accuracy (%) | 72.9 |
| Tau2-Bench Telecom | 68.42 | Success Rate (%) | 63 |
| AA TAU-2 Bench | 68.42 | Accuracy (%) | 61.6 |
| AA CritPt | 1.14 | Accuracy (%) | 57.1 |
| AA MMLU-Pro | 77.34 | Accuracy (%) | 56.2 |
| AA Humanity's Last Exam | 12.14 | Accuracy (%) | 55.3 |
| AA GPQA Diamond | 71.31 | Accuracy (%) | 50.4 |
| AA Terminal-Bench Hard | 10.61 | Accuracy (%) | 45.1 |
| AA Omniscience - Software Engineering (SWE) - Go | 14 | Accuracy (%) | 41.1 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 23.64 | Accuracy (%) | 36.9 |
Interactive version: theaggregate.ai/model?slug=apriel-v1-5-15b-thinker · How It Works · Data refreshed daily, snapshot 2026-11-08.