Doubao-Seed-1.6 (Thinking): benchmark results

Provider: ByteDance. Released 2025-06-11. Access: API.

Unified ELO 1662 ± 1, rank #270 of 3078 rated models, from 23 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AGI-Eval Community - Cognition83.98Accuracy (%)89.3
AGI-Eval Community - Cognition (English)85.56Accuracy (%)88
AGI-Eval Community - Cognition (Chinese)82.84Accuracy (%)86.2
SuperCLUE-VLM (June 2025) - Overall65.67Score84.6
PHYBench45.53EED Score80.6
AGI-Eval Community - Learning88.97Accuracy (%)80.4
AGI-Eval Community - Learning (English)93.65Accuracy (%)79.7
AGI-Eval Community - Interaction (Chinese)83.23Accuracy (%)79.3
AGI-Eval Community - Subject Reasoning (Chinese)88.73Accuracy (%)77.5
AGI-Eval Community - Interaction84.5Accuracy (%)74.3
AGI-Eval Community - Learning (Chinese)82.49Accuracy (%)73.9
AGI-Eval Community - Subject Knowledge86.04Accuracy (%)70

Interactive version: theaggregate.ai/model?slug=doubao-seed-1-6-thinking · How It Works · Data refreshed daily, snapshot 2026-09-19.