Seed-OSS-36B-Base: benchmark scores, price and ranking
Seed-OSS-36B-Base from ByteDance-Seed ranks #288 of 743 LLMs on the LLMs Tiger aggregate benchmark score (49.2), based on 1 benchmark results captured up to 2026-10-13.
- Organisation
- ByteDance-Seed
- Type
- Open-weight / local model
- Open weights
- Yes
- Aggregate rank
- #288 of 743 (score 49.2)
Across the 1 benchmark where at least ten models are scored, Seed-OSS-36B-Base is in the top 10% on 0 and in the top half on 1.
Seed-OSS-36B-Base benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| MMLU-Pro | 65.1% | #51 of 136 | HuggingFace MMLU-Pro leaderboard | 2026-10-13 |
About Seed-OSS-36B-Base
Seed-OSS-36B-Base is an open-weight model that can run on your own hardware from ByteDance-Seed. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where Seed-OSS-36B-Base stands
On our aggregate score, Seed-OSS-36B-Base is #288 of 743 ranked models, around the middle of the table. Its score is 49.2; the scale is centred on 50, so it sits 0.8 points below the typical model. That beats 61% of the ranked field. Among the 3 ranked ByteDance-Seed models it is #2. The next one up is seed-oss-36b-instruct at 51.3. The next one down is Seed-OSS-36B-Base-woSyn at 48.6.
Seed-OSS-36B-Base, benchmark by benchmark
MMLU-Pro puts Seed-OSS-36B-Base at 65.1%, #51 of 136. That beats 62% of the models tested, but 23.0 points short of Darwin-180B-RSI (88.1%). The results either side are NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16 (65.1%) and Qwen2.5-VL-72B-Instruct (64.9%). It covers 57-subject knowledge + reasoning. The board median is 55.3%, so Seed-OSS-36B-Base is 9.8 points above it. Source: HuggingFace MMLU-Pro leaderboard, captured 2026-10-13.
Reading these numbers
The 1 score on this page comes from 1 source: HuggingFace MMLU-Pro leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #285 gpt-3.5-turbo-1106 (49.2)
- #286 computer-use-preview-2025-03-11 (49.2)
- #287 NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16 (49.2)
- #289 kimi-k2p5 (49.2)
- #290 gpt-5-chat (49.2)
- #291 Claude Code + Qwen3.8-Max-0902 (49.1)
More from ByteDance-Seed
- seed-oss-36b-instruct (#133, 51.3)
- Seed-OSS-36B-Base-woSyn (#341, 48.6)
Compare it on the live leaderboard → · How the aggregate score works