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

BenchmarkScoreOpen rankAll models
MMLU-Pro82.7%#15 / 144#51 / 257

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202567.5%#28 / 82#136 / 270

Reasoning

BenchmarkScoreOpen rankAll models
Chess Puzzles13.0%#18 / 65#114 / 205
GPQA Diamond71.5%#29 / 94#159 / 289

Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.