Models / Devstral 2

Mistral AI

Devstral 2

Early evidence, 12 results from 1 source, on 2 use cases. Devstral 2 trails most of the field on what it has been measured on; there is too little evidence yet to recommend it either way. The cheapest model of similar intelligence is Gemma 3 4B, at $0.04 per million tokens against $0.80.

Results 19 Nov 2026 · 12 results · 1 source

Test Devstral 2 on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.40 in · $2.00 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
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 published
Released
9 Dec 2025 (Artificial Analysis)
262,144 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 147th of 185Claude Opus 5.5 – $0.80 blended, 50th percentilecheapest: Mistral Nemo –
Models priced $0.25–1 per million tokens 51st of 61MiMo-V2.6-Pro – sets this group –
Models with similar intelligence sets this group – $0.80 blended, 84th percentilecheapest: Gemma 3 4B –
Models from developers based in the EUall Mistral AI's 7th of 15Mistral Large 4 – $0.80 blended, 60th percentilecheapest: Mistral Nemo –
Open-weights models 75th of 104MiMo-V2.6-Pro – $0.80 blended, 71st percentilecheapest: Mistral Nemo –

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, then those priced $0.25–1 per million tokens. 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 Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 114th of 159 available · 31st of 47 at its price
BenchmarkDevstral 2Rank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 0.0% 67th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 30.3% 76th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 10.5% 69th of 104 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 Not measured
  • 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 154th of 187 available · 53rd of 61 at its price
BenchmarkDevstral 2Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 8.6 147th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 3.6% 177th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 59.4% 133rd of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality Not measured
  • Arena (formerly LMArena): has not measured this model.
  • UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers Not measured
  • 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) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

  • Cheaper at similar intelligenceGemma 3 4B$0.04 blended · Intelligence Index 4.8
  • Mistral AI's newer, at least as capable modelMistral Large 4$2.06 blended · Intelligence Index 38.4

Against Devstral 2 at $0.80 blended, Intelligence Index 8.6. "Similar intelligence" means within 4 points or better.

Where to run it

1 host on OpenRouter at the standard service tier, with a median of $0.80 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Mistralnot stated$0.40$2.00$0.80

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

Devstral 2MiMo-V2.6-Pro
most intelligent at $0.25–1 per million tokens
Gemma 3 4B
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
Mistral Large 4
most intelligent from the EU
Price per million tokens $0.80 $0.54$0.04$8.00$2.06
Tokens a second – 43–9660
Intelligence Index 8.6 46.34.857.638.4
Spring Prompt overall – ––8024
Rank among available models, by use case
Product listings – ––16th30th
Decks from an analysis – ––8th33rd
User surveys – ––5th19th
Marketing planning – ––11th26th
Agents and tool use 114th of 159 23rd158th3rd37th
Professional work – ––3rd–
Reasoning and knowledge 154th of 187 13th181st1st54th
Writing – 23rd157th5th–
Sticking to the facts – 10th32nd3rd–
Speed under pressure – –––27th

Shaded figures are better than Devstral 2's. A dash means no result.

Where it has been measured

51st most intelligent of the 61 models priced $0.25–1 per million tokens. Among models available today, in the bottom quarter for reasoning and knowledge.

Artificial Analysis lists it but has not published a speed for it yet

Every result

12 published results from 1 source, each in the source's own units, with the configuration that produced it.

Artificial Analysis · reported by Artificial Analysis · 12 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 31.3 133 of 187 Devstral 2 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 8.6 344 of 413 Devstral 2 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 59.4% 295 of 360 Devstral 2 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 3.6% 401 of 419 Devstral 2 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 38.1% 217 of 288 Devstral 2 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 32.3% 333 of 407 Devstral 2 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 32.8% 187 of 205 Devstral 2 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 30.3% 133 of 188 Devstral 2 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 Devstral 2 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 18.9% 150 of 282 Devstral 2 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 10.5% 121 of 175 Devstral 2 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 24.9% 236 of 286 Devstral 2 20 Oct 2026

Not shown: Not your codebase or tools.

Will Devstral 2 work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.