Seed OSS 36B Instruct — Benchmarks
Benchmark scores for Seed OSS 36B Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #7 of 78 open modelscomposite 61.2/100 across 4 benchmarks in 3 categories · methodology
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| MMLU-Pro | 82.7% | #15 / 144 | #51 / 257 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 67.5% | #28 / 82 | #136 / 270 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| Chess Puzzles | 13.0% | #18 / 65 | #114 / 205 |
| GPQA Diamond | 71.5% | #29 / 94 | #159 / 289 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.