Seed-1.6 (Thinking): benchmark results
Provider: ByteDance. Released 2025-06-11. Access: API.
Aggregate Rating 1588 ± 22, rank #760 of 2170 rated models, from 31 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM2014 Logic 2025-06 | 71.7 | Median Score | 94.4 |
| LLM2014 Code 2025-09 - Golang | 6.18 | Score | 89.5 |
| MathVision | 77.2 | Overall Accuracy (%) | 89.2 |
| MMMU Benchmark | 74.8 | Validation Score | 87.2 |
| Math-VR | 58.4 | Overall Answer Correctness (imported) | 82.8 |
| LLM2014 Logic 2025-09 | 49.28 | Median Score | 80 |
| LLM2014 Logic 2025-08 | 52.17 | Median Score | 77.3 |
| LLM2014 Logic 2025-10 | 50.35 | Median Score | 75.5 |
| MMTIT-Bench - Other to Chinese | 78.77 | COMET-22 score times 100 (0-100) of end-to-end text-image tr | 71.4 |
| MMTIT-Bench - Other to English | 76.23 | COMET-22 score times 100 (0-100) of end-to-end text-image tr | 71.4 |
| MolRecBench-Wild - Graph | 4.61 | Graph exact-match accuracy (%; CARBON graph with atom types, | 71.4 |
| LLM2014 Code 2025-09 - Java | 5.66 | Score | 63.2 |
Interactive version: theaggregate.ai/model?slug=seed-1-6-thinking · How It Works · Data refreshed daily, snapshot 2026-11-05.