Compare / Ministral 3 3B vs Qwen3.5 2B
Ministral 3 3B vs Qwen3.5 2B
Updated November 2026
Verdict
Ministral 3 3B scores higher on the Small LM Index: 49.4 vs 33.0. On the 1 benchmark both labs report, Ministral 3 3B wins 1 and Qwen3.5 2B wins 0. Both need about 3.3 GB of memory at 4-bit quantization. Only Ministral 3 3B has a hosted API on OpenRouter ($0.10 per million tokens); the other has to be self-hosted.
Pick Ministral 3 3B if…
- you want the strongest model overall
- you want a hosted API rather than running it yourself
Pick Qwen3.5 2B if…
- you work with long documents
- you want the more widely used model (more quantized builds and community support)
Specifications
| Ministral 3 3B | Qwen3.5 2B | |
|---|---|---|
| Small LM Index | 49.4 (likely 45–54) | 33.0 (likely 29–37) |
| Lab | Mistral AI · Europe | Alibaba (Qwen) · China |
| Released | 2025-12-02 | 2026-03-02 |
| Parameters | 3B (dense) | 2.3B (dense) |
| Memory at 4-bit | ~3.3 GB | ~2 GB |
| Context window | 256K tokens | 262K tokens |
| Input | text, image | text, image, video |
| Reasoning | Hybrid (thinking on/off) | Hybrid (thinking on/off) |
| License | Apache-2.0 | Apache-2.0 |
| API price / 1M tokens | $0.10 ($0.10 in, $0.10 out) | Self-host only |
| Hugging Face downloads (30 days) | 17.7K | 3.4M |
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 | Ministral 3 3B | Qwen3.5 2B |
|---|---|---|
| MMLU-Pro Knowledge | ≈ 72 | 66.5 |
| GPQA Diamond Knowledge | 53.4 | 51.6 |
| AIME Math | 72.1 | ≈ 39 |
| LiveCodeBench Coding | 54.8 | ≈ 36 |
| τ²-Bench Agentic | — | 48.8 |
| IFBench Instruction following | — | 41.3 |
| MMLU Knowledge | — | 79.6 |
| Multilingual MMLU Multilingual | — | 63.1 |
| IFEval Instruction following | — | 78.6 |
| BFCL Agentic | — | 43.6 |
| HMMT Math | — | 22.9 |
| AA-LCR Long context | — | 25.6 |
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, Ministral 3 3B or Qwen3.5 2B?
Ministral 3 3B scores higher on the Small LM Index: 49.4 vs 33.0. On the 1 benchmark both labs report, Ministral 3 3B wins 1 and Qwen3.5 2B wins 0.
Which is cheaper to run?
Only Ministral 3 3B has a hosted API on OpenRouter ($0.10 per million tokens); the other has to be self-hosted. Both need about 3.3 GB of memory at 4-bit quantization.
Which has the longer context window?
Qwen3.5 2B has the longer context window: 262K tokens against 256K.
Can I use Ministral 3 3B and Qwen3.5 2B 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.