Doubao-Seed-2.0-lite-0428: benchmark results
Provider: ByteDance.
Aggregate Rating 1794 ± 36, rank #105 of 10916 rated models, from 36 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MathVision | 89.8 | Overall Accuracy (%) | 98.4 |
| EvoGUI-Bench | 50.7 | EvoGain index (mean over the three probes of the gain over t | 96.3 |
| EvoGUI-Bench - Successor Discrimination | 81.9 | Pairwise successor accuracy (%; share of 1,000 items in whic | 96.3 |
| EvoGUI-Bench - Temporal Ordering | 49.4 | Exact ordering accuracy (%; share of 1,000 sets of 3 to 5 sh | 96.3 |
| MuLA-Bench - Chinese | 66.5 | Accuracy (%; the 337 Chinese-language questions over both ev | 71.4 |
| MuLA-Bench - Acoustic Evidence | 37.81 | Accuracy (%; the 1,198 acoustic-track questions about natura | 66.7 |
| MuLA-Bench - Factual | 59.97 | Accuracy (%; the 1,891 factual and completeness questions (s | 66.7 |
| MuLA-Bench - English | 65.1 | Accuracy (%; the 347 English-language questions over both ev | 57.1 |
| MuLA-Bench - Entertainment Domain | 64.4 | Accuracy (%; the 480 semantic-track questions from entertain | 57.1 |
| MuLA-Bench - Indonesian | 59.3 | Accuracy (%; the 324 Indonesian-language questions over both | 57.1 |
| MuLA-Bench - Lifestyle Domain | 66.7 | Accuracy (%; the 480 semantic-track questions from lifestyle | 57.1 |
| MuLA-Bench | 56.91 | Accuracy (%; all 5,038 questions over 1,769 recordings in 16 | 55.6 |
Interactive version: theaggregate.ai/model?slug=doubao-seed-2-0-lite-0428 · How It Works · Data refreshed daily, snapshot 2026-11-08.