Doubao-1.5-Pro-32k: benchmark results
Provider: ByteDance. Access: Open.
Unified ELO 1700 ± 33, rank #350 of 2928 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SuperCLUE-Faith (May 2025) - Overall | 95.89 | Accuracy (%) | 100 |
| Web-Bench | 16.6 | Pass@1 (%) | 63.8 |
| AGI-Eval Community - Cognition (English) | 80.71 | Accuracy (%) | 62.3 |
| AGI-Eval Community - Learning (Chinese) | 77.14 | Accuracy (%) | 45.7 |
| SuperCLUE-Fact - Overall | 81.72 | Score | 44.4 |
| AGI-Eval Community - Cognition | 76.56 | Accuracy (%) | 42.5 |
| AGI-Eval Community - Instruction Following | 34.89 | Accuracy (%) | 39.3 |
| AGI-Eval Community - Cognition (Chinese) | 73.55 | Accuracy (%) | 37 |
| AGI-Eval Community - Subject Reasoning (Chinese) | 74.73 | Accuracy (%) | 34.1 |
| AGI-Eval Community - Subject Knowledge | 79.47 | Accuracy (%) | 31.4 |
| AGI-Eval Community - Interaction (English) | 87.18 | Accuracy (%) | 29 |
| AGI-Eval Community - Subject Reasoning | 75.79 | Accuracy (%) | 27.9 |
Interactive version: theaggregate.ai/model?slug=doubao-1-5-pro-32k · How It Works · Data refreshed daily, snapshot 2026-09-23.