Compare / Devstral Small 2 vs GPT-6.1 Sol

Devstral Small 2 vs GPT-6.1 Sol

Which is cheaper, which is more capable, and which does better at each kind of work, from 8 results on 2 sources that measured both models.

Mistral AIDevstral Small 2 Released 9 Dec 2025 · Not on sale
OpenAIGPT-6.1 Sol Released 29 Sep 2026 · $2.00 in · $10.00 out
Devstral Small 2 wins 0GPT-6.1 Sol wins 8

Of the 8 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee). See also Mistral AI vs OpenAI, every model from both labs.

Devstral Small 2 or GPT-6.1 Sol? The short answer

Pick GPT-6.1 Sol: it scores higher (Intelligence Index 51.8 against 7.5) at about the same price.

  • GPT-6.1 Sol scores higher on the Artificial Analysis Intelligence Index: 51.8 against 7.5.
  • GPT-6.1 Sol is newer: released 29 Sep 2026, against 9 Dec 2025 for Devstral Small 2.
  • On third-party benchmarks, on the results both models have: GPT-6.1 Sol does better for agents and tool use, reasoning and knowledge and writing.

Head to head

7.5
Intelligence Index
51.8

Every fact side by side

Devstral Small 2GPT-6.1 Sol
Price per million tokensNot on sale$2.00 in · $10.00 out
Blended (3 in : 1 out)–$4.00
Cheapest host, blended–$4.00 (Amazon Bedrock)
Cached input, per million–$0.10 cached input
Intelligence Index7.551.8
Spring Prompt overall–80
Output speed, tokens a second–53
Context window–1,050,000 tokens
Released9 Dec 202529 Sep 2026 (newer)
WeightsClosedClosed
Developer based inFrancethe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live not measured 2 of 32
Decks from an analysisTurning a finished analysis into a deck you could present as it is not measured 5 of 32
User surveysPlanning a user survey and reading its results without being misled not measured 3 of 23
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 114 of 160 6 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 9 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 162 of 188 6 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 133 of 170 16 of 169
Sticking to the factsSummarising without inventing things, and factual answers not measured 18 of 139
Speed under pressureGood decisions against a real clock (fast chess) not measured 3 of 35

From our research

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureDevstral Small 2GPT-6.1 Sol
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 211 · 7 of 249 measured 7.5 51.8max reasoning
Humanity's Last Exam% of questions, higher is better 242 · 8 of 250 measured 3.5% 52.9%max reasoning
Terminal-Bench 4.0% of tasks, higher is better 72 · 6 of 120 measured 0.0% 56.1%max reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 146 · 17 of 230 measured 31.6 67.7high reasoning
Requested-length error · UGI% off the requested word count, lower is better 151 · 1 of 230 measured 26.0% 0.0%high reasoning
Style adherence · UGIscore from 0 to 1, higher is better 113 · 39 of 230 measured 0.35 0.37high reasoning
Show all 8 results (2 more)
MeasureDevstral Small 2GPT-6.1 Sol
Artificial Analysis reported by Artificial Analysis · 2 results
Long-context reasoning (AA-LCR)% of questions, higher is better 196 · 7 of 241 measured 28.0% 84.0%low reasoning
SciCode% of problems, higher is better 104 · 26 of 121 measured 32.4% 55.8%high reasoning

Quick answers

Is Devstral Small 2 better than GPT-6.1 Sol?

Pick GPT-6.1 Sol: it scores higher (Intelligence Index 51.8 against 7.5) at about the same price.

Which is better for agents and tool use, Devstral Small 2 or GPT-6.1 Sol?

GPT-6.1 Sol ranks 6 of 160 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 114 for Devstral Small 2.

Which is better for reasoning and knowledge, Devstral Small 2 or GPT-6.1 Sol?

GPT-6.1 Sol ranks 6 of 188 models on sale for hard questions across science, maths and general knowledge, against 162 for Devstral Small 2.

Which is better for writing, Devstral Small 2 or GPT-6.1 Sol?

GPT-6.1 Sol ranks 16 of 170 models on sale for what people prefer in blind comparisons, and judged writing quality, against 133 for Devstral Small 2.

Run Devstral Small 2 and GPT-6.1 Sol on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.