Magistral Small 1.2
Analysis Summary
Mistral's Magistral Small 1.2 is a small reasoning-oriented model with mixed task results. Its LiveCodeBench result is comparatively strong against its low general intelligence and coding index, and its math performance is useful for selected problems. However, instruction following, long-context performance, and tau2 are weak, giving little evidence for dependable multi-step or agentic behavior.
This makes it a candidate for inexpensive, tightly scoped coding or math experiments, not a primary model for software engineering agents or polished client content. Its listed input and output prices are relatively low, which can support controlled testing, but value depends on whether the model completes tasks reliably without repeated retries or human correction. Teams should benchmark it on their own code and prompts before routing production traffic. The current evidence supports a specialist trial with review, rather than broad adoption.
Assessed September 23, 2026
Editorial notes
Magistral Small 1.2 pairs low listed pricing with a strong coding-task result, but its intelligence, instruction-following, long-context, and agentic measures are limited.
The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?
DFO Verdict
Magistral Small 1.2 pairs low listed pricing with a strong coding-task result, but its intelligence, instruction-following, long-context, and agentic measures are limited.
Benchmarks
Artificial Analysis data refreshed Nov 7, 2026. Arena ratings from the Oct 28, 2026 text leaderboard, with style control. Bars: magenta = reasoning, ink = coding and agents, cyan = instructions and long context.
Artificial Analysis no longer lists this model, so its indexes are converted from their older scale to stay comparable.
How Magistral Small 1.2 compares
Magistral Small 1.2 ranks #271 of 447 AI models we track for overall intelligence, #156 of 199 for coding, #143 of 181 for agentic tasks. At $0.50 per million input tokens it is cheaper than 35% of comparable models.
Dark bar = input · light bar = output, scaled to the priciest peer.
1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.50 | $0.000500 |
| Output | $1.50 | $0.001500 |
What would Magistral Small 1.2 cost your business?
Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.
A website chatbot handling around 100 customer conversations a day, a few short messages each.
Full calculator with 733 models → Price Calculator
These numbers get smaller with the right architecture.
We route routine calls to cheap models and save Magistral Small 1.2 for the hard ones. Most clients cut their estimate by 60-80%.
Talk to our teamFrequently asked questions about Magistral Small 1.2
How much does Magistral Small 1.2 cost?
Magistral Small 1.2 costs $0.50 per million input tokens and $1.50 per million output tokens.
Is Magistral Small 1.2 good for coding?
On our coding benchmark index, Magistral Small 1.2 ranks #156 of 199 models, placing it in the broader range of the field for code generation and debugging.
Who created Magistral Small 1.2?
Magistral Small 1.2 is developed by Mistral and was released on September 17, 2025.