tinyanalysis

Compare / Magistral Small 1.2 vs Devstral Small 2

Magistral Small 1.2 vs Devstral Small 2

Updated November 2026

Verdict

Magistral Small 1.2 scores higher on the Small LM Index: 58.6 vs 37.3. On the 8 benchmarks both labs report, Magistral Small 1.2 wins 7 and Devstral Small 2 wins 1. Both need about 16.9 GB of memory at 4-bit quantization. Neither model has a hosted API on OpenRouter, so you would run both yourself.

Pick Magistral Small 1.2 if…

  • you want the strongest model overall
  • you mostly write code
  • you need math and reasoning
  • you need precise instruction following
  • you build agents that call tools

Pick Devstral Small 2 if…

  • you work with long documents
  • you want the more widely used model (more quantized builds and community support)

Specifications

Magistral Small 1.2Devstral Small 2
Small LM Index58.6 (likely 56–61)37.3 (likely 34–40)
LabMistral AI · EuropeMistral AI · Europe
Released2025-09-172025-12-09
Parameters24B (dense)24B (dense)
Memory at 4-bit~16.9 GB~16.9 GB
Context window128K tokens256K tokens
Inputtext, imagetext, image
ReasoningAlways thinksNo thinking
LicenseApache-2.0Apache-2.0
API price / 1M tokensSelf-host onlySelf-host only
Hugging Face downloads (30 days)29.8K123.7K

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.

BenchmarkMagistral Small 1.2Devstral Small 2
MMLU-Pro Knowledge76.8✓67.8✓
GPQA Diamond Knowledge66.3✓53.2✓
Humanity's Last Exam Reasoning6.4✓3.5✓
AIME Math80.3✓34.3✓
LiveCodeBench Coding72.3✓34.8✓
SWE-bench Verified Coding≈ 5268.0
Terminal-Bench Agentic—22.5*
τ²-Bench Agentic27.8✓23.4✓
IFBench Instruction following44.4✓31.2✓
AA-LCR Long context19.3✓28.0✓
SciCode Coding—32.4✓

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, Magistral Small 1.2 or Devstral Small 2?

Magistral Small 1.2 scores higher on the Small LM Index: 58.6 vs 37.3. On the 8 benchmarks both labs report, Magistral Small 1.2 wins 7 and Devstral Small 2 wins 1.

Which is cheaper to run?

Neither model has a hosted API on OpenRouter, so you would run both yourself. Both need about 16.9 GB of memory at 4-bit quantization.

Which has the longer context window?

Devstral Small 2 has the longer context window: 256K tokens against 128K.

Can I use Magistral Small 1.2 and Devstral Small 2 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

Guides featuring these models