ByteDanceOpen weights: ByteDance-Seed/Seed-OSS-36B-InstructReasoning modelCompare with another modelSeed-OSS-36B-Instruct
Seed-OSS-36B-Instruct is a ByteDance open-weights reasoning model, released 20 Aug 2025. Its best configuration ranks #474 of 785 on the BenchLeader Index at 46.8 ±4.4, in the lower half. The ± is the point: 309 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in long context (55) and lowest in knowledge (38). At $0.300 per million tokens blended it is cheaper than most ranked models. Output speed of 38 tokens per second puts it in the slowest quarter, with a first answer in 55.5 s. Last measured 20 Aug 2025.stale: no new result in six months
- Blended price
- $0.300/M
- $0.210 in · $0.570 out
- Output speed
- 38 tok/s
- measured by Artificial Analysis
- First answer
- 56 s
- Context
- 512k
- Full answer
- 69 s
- median, reasoning included
- Cost per run
- –
- Released
- 20 Aug 2025
- Overall index47
- Reasoning47
- Agents & tools40
- Maths53
- Knowledge38
- Instruction following44
- Long context55
- Composite43
How its index has moved
9 Sept 2026 to 23 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source |
|---|---|---|
| GPQA Diamond | 71.5%#167 | Epoch AI Benchmarking Hub |
| GPQA Diamond (AA)not in index | 72.6%#277 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 9.9%#326 | Artificial Analysis |
| CritPt | 0.0%#315 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source |
|---|---|---|
| Terminal-Bench Hard | 6.8%#249 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 49.4%#198 | Artificial Analysis |
Maths
| Benchmark | not stated | Source |
|---|---|---|
| OTIS Mock AIME | 67.5%#147 | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | not stated | Source |
|---|---|---|
| AA-Omniscience | -52.5#410 | Artificial Analysis |
| AA-Omniscience: accuracynot in index | 18.2%#342 | Artificial Analysis |
| AA-Omniscience: non-hallucinationnot in index | 13.6%#359 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source |
|---|---|---|
| IFBench | 41.9%#241 | Artificial Analysis |
Long context
| Benchmark | not stated | Source |
|---|---|---|
| AA-LCR | 61.3%#273 | Artificial Analysis |
Composite
| Benchmark | not stated | Source |
|---|---|---|
| AA Intelligence Index v4.3.2 | 12.1#338 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0003 | – | 1.1 min |
| Summarize a 30-page report | 12,000 / 600 | $0.0029 | – | 1.2 min |
| Code edit | 6,000 / 1,500 | $0.0021 | – | 1.6 min |
| Agentic coding session | 60,000 / 4,000 | $0.015 | – | 2.7 min |
| Structured extraction | 2,000 / 200 | $0.0005 | – | 1.0 min |
More from ByteDance
See also
Questions people ask
- What are Seed-OSS-36B-Instruct's benchmark scores?
- As of 25 Oct 2026, Seed-OSS-36B-Instruct scores 46.8 ±4.4 on the BenchLeader Index, strongest in long context (55) and weakest in knowledge (38). That rests on 8 independent benchmark results, and every score on this page links to its publisher.
- How does Seed-OSS-36B-Instruct rank?
- Seed-OSS-36B-Instruct is #474 of 785 ranked configurations on 25 Oct 2026. 309 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Seed-OSS-36B-Instruct cost per 1M tokens?
- As of 25 Oct 2026, Seed-OSS-36B-Instruct costs $0.210 per 1M input tokens and $0.570 per 1M output tokens, $0.300 blended (three input tokens per output token).
- When was Seed-OSS-36B-Instruct released?
- ByteDance released Seed-OSS-36B-Instruct on 20 Aug 2025.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Seed-OSS-36B-Instruct: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/seed-oss-36b.