Models / Magistral Small 1.2
Magistral Small 1.2
Magistral Small 1.2 trails most of the field on what it has been measured on; it is not on sale through OpenRouter, so it is here for reference.
Results 16 Nov 2026 · 18 results · 2 sources
- Price per million tokens
- Not available through OpenRouter
- Speed
- 76 tokens a second; on its test prompt the answer starts after 27.1 s, thinking time included
Artificial Analysis, on its usual API - Intelligence Index
- 8.6
Artificial Analysis - Spring Prompt overall
- Not ranked yet
needs our benchmarks and two groups of results - Developer
- Mistral AI, based in France
Weights not published - Released
- 17 Sep 2025 (Artificial Analysis)
Where it stands among the models you could choose
Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.
| Among | Intelligence Index | Spring Prompt overall | Price, blended | Speed |
|---|---|---|---|---|
| Models available today | 147th of 186Claude Opus 5.5 | – | – | 47th of 66Nemotron 3.5 Super VL |
| Models with similar intelligence | sets this group | – | – | 14th of 18gpt-oss-20b |
| Models writing 50–100 tokens a second | 17th of 22Claude Opus 5.5 | – | – | sets this group |
| Models from developers based in the EUall Mistral AI's | 7th of 16Mistral Large 4 | – | – | 6th of 7Ministral 3 3B |
The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.
How good is it, and for what?
Each use case ranks the available models its benchmarks measured. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.
Product listingsTurning a sparse product feed and photos into listings that can go live
- CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is
- DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled
- SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending
- ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls
| Benchmark | Magistral Small 1.2 | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported | 4.5% | 99th of 108 | Claude Fable 5.1 91.4% |
| Artificial AnalysisArtificial Analysis: τ-bench banking · reported | 4.5% | 97th of 105 | Grok 4.6 50.7% |
- tau2-bench: has not measured this model.
- Berkeley Function Calling Leaderboard (BFCL) V4: has not measured this model.
- OpenHands Index: has not measured this model.
- Microsoft STATE-Bench: has not measured this model.
- Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects
- APEX-Agents: has not measured this model.
- GDP.pdf: has not measured this model.
- Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge
| Benchmark | Magistral Small 1.2 | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported | 8.6 | 147th of 186 | Claude Opus 5.5 57.6 |
| Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported | 6.4% | 141st of 187 | Claude Opus 5.5 61.4% |
| Artificial AnalysisArtificial Analysis: GPQA Diamond · reported | 66.3% | 126th of 169 | GPT-6 Astra 96.3% |
WritingWhat people prefer in blind comparisons, and judged writing quality
| Benchmark | Magistral Small 1.2 | Rank among available | Best available |
|---|---|---|---|
| UGI LeaderboardUGI: writing score · reported | 34.0 | 92nd of 125 | Gemini 3.8 Flash 78.6 |
- Arena (formerly LMArena): has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers
- Vectara Hallucination Leaderboard: has not measured this model.
- Arena (formerly LMArena): has not measured this model.
- SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess)
- BulletBench: has not measured this model.
Nearest alternatives
- Mistral AI's newer, at least as capable modelMistral Large 4$2.06 blended · Intelligence Index 38.4
- Open weights at similar intelligenceGemma 3 4B$0.04 blended · Intelligence Index 4.8Compare with Magistral Small 1.2 →
Against Magistral Small 1.2, Intelligence Index 8.6. "Similar intelligence" means within 4 points or better.
Against the alternatives
The models you would most likely weigh it against: the leaders of the groups above.
Scroll sideways to see every alternative.
| Magistral Small 1.2 | gpt-oss-20b fastest with similar intelligence | Claude Opus 5.5 most intelligent available today | Mistral Large 4 most intelligent from the EU | |
|---|---|---|---|---|
| Price per million tokens | – | $0.06 | $8.00 | $2.06 |
| Tokens a second | 76 | 277 | 96 | 60 |
| Intelligence Index | 8.6 | 10.0 | 57.6 | 38.4 |
| Spring Prompt overall | – | – | 82 | 25 |
| Rank among available models, by use case | ||||
| Product listings | – | – | 13th | 27th |
| Decks from an analysis | – | – | 7th | 30th |
| User surveys | – | – | 4th | 17th |
| Marketing planning | – | – | 9th | 23rd |
| Agents and tool use | 154th of 160 | 129th | 3rd | 38th |
| Professional work | – | – | 3rd | – |
| Reasoning and knowledge | 142nd of 188 | 132nd | 1st | 54th |
| Writing | 125th of 170 | 156th | 5th | – |
| Sticking to the facts | – | – | 3rd | – |
| Speed under pressure | – | – | – | 25th |
| Side by side → | Side by side → | |||
Shaded figures are better than Magistral Small 1.2's. A dash means no result.
Where it has been measured
Compared with the models available today (it is not on sale itself), in the bottom quarter for agents and tool use, and reasoning and knowledge.
- Artificial Analysis12 results
- UGI Leaderboard6 results
- BulletBenchNot measured
- CatalogBenchNot measured
- DeckBenchNot measured
- ROASBenchNot measured
- SurveyBenchNot measured
- APEX-AgentsNot measured
- Arena (formerly LMArena)Not measured
- Berkeley Function Calling Leaderboard (BFCL) V4Not measured
- GDP.pdfNot measured
- Microsoft STATE-BenchNot measured
- OpenHands IndexNot measured
- Remote Labor IndexNot measured
- SimpleQA Verified (Epoch AI)Not measured
- tau2-benchNot measured
- Vectara Hallucination LeaderboardNot measured
- Vending-Bench 2Not measured
Every result
18 published results from 2 sources, each in the source's own units, with the configuration that produced it.
Artificial Analysis · reported by Artificial Analysis · 12 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better | 14.7 | 166 of 187 | Magistral Small 1.2 | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 8.6 | 344 of 413 | Magistral Small 1.2 | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 66.3% | 273 of 360 | Magistral Small 1.2 | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 6.4% | 323 of 419 | Magistral Small 1.2 | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 44.4% | 172 of 288 | Magistral Small 1.2 | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 19.3% | 366 of 407 | Magistral Small 1.2 | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 76.0 | 88 of 137 | Magistral Small 1.2 | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better | 4.5% | 170 of 188 | Magistral Small 1.2 | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 4.5% | 237 of 282 | Magistral Small 1.2 | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 27.1 | 94 of 137 | Magistral Small 1.2 | 20 Oct 2026 |
| Artificial Analysis: τ-bench banking% of tasks, higher is better | 4.5% | 165 of 175 | Magistral Small 1.2 | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 27.8% | 223 of 286 | Magistral Small 1.2 | 20 Oct 2026 |
Not shown: Not your codebase or tools.
UGI Leaderboard · reported by UGI Leaderboard · 6 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| UGI: requested-length error% off the requested word count, lower is better | 17.0% | 148 of 379 | Magistral Small 1.2 | 7 Oct 2025 |
| UGI: requested-length error% off the requested word count, lower is better | 197.0% | 376 of 379 | Magistral Small 1.2 (magistral-sys-prompt reasoning) | 30 Sep 2025 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.34 | 224 of 379 | Magistral Small 1.2 | 7 Oct 2025 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.30 | 339 of 379 | Magistral Small 1.2 (magistral-sys-prompt reasoning) | 30 Sep 2025 |
| UGI: writing scorescore out of 100, higher is better | 34.0 | 253 of 379 | Magistral Small 1.2 | 7 Oct 2025 |
| UGI: writing scorescore out of 100, higher is better | 19.2 | 348 of 379 | Magistral Small 1.2 (magistral-sys-prompt reasoning) | 30 Sep 2025 |
Not shown: Not other format limits such as character counts or bullet counts.
Test your own prompt.
Benchmarks aren't your task. Run your prompt on the models you could use, with every answer checked and costed.