Compare / Seed-OSS 36B Instruct vs MiniCPM-V 4.7 35B-A3B
Seed-OSS 36B Instruct vs MiniCPM-V 4.7 35B-A3B
Updated November 2026
Verdict
Seed-OSS 36B Instruct scores higher on the Small LM Index: 60.3 vs 54.5, although their likely ranges overlap, so the lead is not certain. On the 3 benchmarks both labs report, Seed-OSS 36B Instruct wins 2 and MiniCPM-V 4.7 35B-A3B wins 1. MiniCPM-V 4.7 35B-A3B is smaller: it needs about 22.7 GB of memory at 4-bit, against 25.3 GB for Seed-OSS 36B Instruct. Neither model has a hosted API on OpenRouter, so you would run both yourself.
Pick Seed-OSS 36B Instruct if…
- you want the strongest model overall
- you mostly write code
- you need math and reasoning
- you work with long documents
Pick MiniCPM-V 4.7 35B-A3B if…
- you have limited memory (about 22.7 GB at 4-bit)
- you need image input
- you want the more widely used model (more quantized builds and community support)
Specifications
| Seed-OSS 36B Instruct | MiniCPM-V 4.7 35B-A3B | |
|---|---|---|
| Small LM Index | 60.3 (likely 57–64) | 54.5 (likely 50–59) |
| Lab | ByteDance Seed · China | OpenBMB (MiniCPM) · China |
| Released | 2025-08-20 | 2026-10-07 |
| Parameters | 36.2B (dense) | 35.2B (3B active, MoE) |
| Memory at 4-bit | ~25.3 GB | ~22.7 GB |
| Context window | 512K tokens | 262K tokens |
| Input | text | text, image, video |
| Reasoning | Always thinks | Hybrid (thinking on/off) |
| License | Apache-2.0 | Apache-2.0 |
| API price / 1M tokens | Self-host only | Self-host only |
| Hugging Face downloads (30 days) | 40.7K | 490.1K |
Benchmarks
Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.
| Benchmark | Seed-OSS 36B Instruct | MiniCPM-V 4.7 35B-A3B |
|---|---|---|
| MMLU-Pro Knowledge | 82.7 | 83.5 |
| GPQA Diamond Knowledge | 71.4 | ≈ 68 |
| Humanity's Last Exam Reasoning | 10.1 | ≈ 8 |
| AIME Math | 84.7 | 76.5 |
| LiveCodeBench Coding | 67.4 | 56.6 |
| SWE-bench Verified Coding | 56.0 | ≈ 37 |
| τ²-Bench Agentic | — | 84.7 |
| IFBench Instruction following | — | 47.7 |
| MMLU Knowledge | 87.4 | — |
| Multilingual MMLU Multilingual | 78.4 | — |
| IFEval Instruction following | 85.8 | — |
| BFCL Agentic | — | 60.1 |
Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.
Questions
Which is better, Seed-OSS 36B Instruct or MiniCPM-V 4.7 35B-A3B?
Seed-OSS 36B Instruct scores higher on the Small LM Index: 60.3 vs 54.5, although their likely ranges overlap, so the lead is not certain. On the 3 benchmarks both labs report, Seed-OSS 36B Instruct wins 2 and MiniCPM-V 4.7 35B-A3B wins 1.
Which is cheaper to run?
Neither model has a hosted API on OpenRouter, so you would run both yourself. MiniCPM-V 4.7 35B-A3B is smaller: it needs about 22.7 GB of memory at 4-bit, against 25.3 GB for Seed-OSS 36B Instruct.
Which has the longer context window?
Seed-OSS 36B Instruct has the longer context window: 512K tokens against 262K.
Can I use Seed-OSS 36B Instruct and MiniCPM-V 4.7 35B-A3B commercially?
Both are released under the Apache-2.0 license. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.
Related comparisons
- Qwen3.6 35B-A3B vs Seed-OSS 36B Instruct
- Qwen3.5 35B-A3B vs Seed-OSS 36B Instruct
- Edge0 35B-A3B (preview) vs Seed-OSS 36B Instruct
- Hermes 4.3 36B vs Seed-OSS 36B Instruct
- MiniCPM-V 4.7 35B-A3B vs Qwen3.6 35B-A3B
- MiniCPM-V 4.7 35B-A3B vs Qwen3.5 35B-A3B
- Edge0 35B-A3B (preview) vs MiniCPM-V 4.7 35B-A3B
- Hermes 4.3 36B vs MiniCPM-V 4.7 35B-A3B