Doubao-Seed-2.1-Lite: benchmark results
Provider: ByteDance. Access: API.
Aggregate Rating 1750 ± 45, rank #172 of 10552 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| XBot Study - ERIBench Safety Boundary | 62.25 | Task-specific accuracy (%) | 100 |
| XBot Study - EgoProx Exploration Approximate | 41.71 | Task-specific accuracy (%) | 100 |
| XBot Study - EgoProx Intention Approximate | 39.9 | Task-specific accuracy (%) | 100 |
| XBot Study - ReTurn Overall | 70.04 | Task-specific accuracy (%) | 100 |
| XBot Study - ReTurn Rebind | 55.04 | Task-specific accuracy (%) | 100 |
| XBot Study - ReTurn Reconfirm | 98.24 | Task-specific accuracy (%) | 100 |
| XBot Study - ReTurn Reground | 29.6 | Task-specific accuracy (%) | 100 |
| XBot Study - ReTurn Retrieve | 97.28 | Task-specific accuracy (%) | 100 |
| EvaOmni - Basic Understanding - Coverage Grounded Score | 61.5 | Score (%) | 91.3 |
| EvaOmni - Overall - Coverage Grounded Score | 64.3 | Score (%) | 87 |
| EvaOmni - Recognition and Grounding - Answer Accuracy | 78.8 | Score (%) | 87 |
| EvaOmni - Recognition and Grounding - Coverage Grounded Score | 74.8 | Score (%) | 87 |
Interactive version: theaggregate.ai/model?slug=doubao-seed-2-1-lite · How It Works · Data refreshed daily, snapshot 2026-11-16.