Doubao-1.5-pro-32k-250115: benchmark results
ByteDance's Doubao-1.5-pro-32k (January 2025), a sparse Mixture-of-Experts model with a 32K-token context, served on Volcano Engine. Provider: ByteDance. Released 2025-01-22. Access: API.
Aggregate Rating 1650 ± 34, rank #320 of 1635 rated models, from 61 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Reasoning - Academic - Chinese (CompassBench 2501) | 82.8 | Score (%) | 100 |
| OpenCompass Reasoning - Academic - English (CompassBench 2501) | 82.7 | Score (%) | 100 |
| OpenCompass LLM - Reasoning - Chinese (CompassBench 2501) | 82.3 | Score (%) | 97.4 |
| OpenCompass LLM - Reasoning (CompassBench 2501) | 81.8 | Score (%) | 96.2 |
| OpenCompass Knowledge - Engineering - English (CompassBench 2501) | 94 | Score (%) | 94.9 |
| OpenCompass LLM - Knowledge - Chinese (CompassBench 2501) | 89.8 | Score (%) | 94.9 |
| OpenCompass LLM - Reasoning - English (CompassBench 2501) | 81.3 | Score (%) | 94.9 |
| SuperCLUE General (March 2025) - Precise Instruction Following | 46.77 | Score | 94.3 |
| SuperCLUE General (March 2025) - Science Reasoning | 70 | Score | 94.3 |
| OpenCompass Reasoning - Puzzle - Chinese (CompassBench 2501) | 86.4 | Score (%) | 92.3 |
| OpenCompass Knowledge - Humanities - English (CompassBench 2501) | 87 | Score (%) | 91 |
| OpenCompass Math - College - Chinese (CompassBench 2501) | 72 | Score (%) | 91 |
Interactive version: theaggregate.ai/model?slug=doubao-1-5-pro-32k-250115 · How It Works · Data refreshed daily, snapshot 2026-11-05.