doubao-seed-1.6-thinking-250615 — benchmark results
Provider: ByteDance. Released 2025-06-25. Access: API.
Unified ELO 1634 ± 19, rank #383 of 1726 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ReliableMath - Prudence | 1 | Score (%) | 94.7 |
| ReliableMath - Precision | 59.4 | Score (%) | 84.2 |
| OpenCompass Research - MMLU-Pro | 83.1 | Score (%) | 67 |
| OpenCompass Research - HLE | 13.5 | Score (%) | 50 |
| OpenCompass Research - AIME 2025 | 82.8 | Score (%) | 44.7 |
| OpenCompass Research - GPQA Diamond | 75.9 | Score (%) | 44.7 |
| OpenCompass Research - LiveCodeBench v6 | 61.8 | Score (%) | 42.6 |
| OpenCompass | 66 | Average Score | 38.3 |
| OpenCompass Research - IFEval | 78.9 | Score (%) | 4.3 |
Interactive version: aibenchmarks.dev/model?slug=doubao-seed-1-6-thinking-250615 · How the rankings work · Data refreshed daily, snapshot 2026-07-08.