Models / Mistral Small 4

Mistral AI

Mistral Small 4

Mistral Small 4 is strongest at speed under pressure; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is gpt-oss-20b, at $0.06 per million tokens against $0.26.

Results 16 Nov 2026 · 39 results · 3 sources

Test Mistral Small 4 on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.15 in · $0.60 out
Mistral AI's list price, 10 Nov 2026 · compare prices$0.01 cached input · 50% off in batch
Speed
176 tokens a second; on its test prompt the answer starts after 12.0 s, thinking time included
Artificial Analysis, on its usual API; 166–176 across 2 settings
Intelligence Index
11.3
Artificial Analysis; 9.0–11.3 across 2 settings
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Mistral AI, based in France
Weights published
Released
16 Mar 2026
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 130th of 185Claude Opus 5.5 – $0.26 blended, 23rd percentilecheapest: Mistral Nemo 17th of 65Nemotron 3.5 Super VL
Models priced $0.25–1 per million tokens 38th of 61MiMo-V2.6-Pro – sets this group 8th of 20Gemini 3.5 Flash-Lite
Models with similar intelligence sets this group – $0.26 blended, 30th percentilecheapest: gpt-oss-20b 5th of 13gpt-oss-20b
Models writing 100–200 tokens a second 19th of 21Claude Sonnet 5.5 – $0.26 blended, 15th percentilecheapest: Qwen3.5-9B sets this group
Models from developers based in the EUall Mistral AI's 3rd of 15Mistral Large 4 – $0.26 blended, 40th percentilecheapest: Mistral Nemo 2nd of 6Ministral 3 3B
Open-weights models 62nd of 104MiMo-V2.6-Pro – $0.26 blended, 34th percentilecheapest: Mistral Nemo 12th of 43Nemotron 3.5 Super VL

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.

Measured cost per task

API cost recorded in our benchmark runs, excluding judging.

TaskBenchmarkCost per task
Game of bullet chessBulletBench≈ $0.004

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 133rd of 159 available · 38th of 47 at its price
BenchmarkMistral Small 4Rank 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 21.0% 81st of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 4.9% 92nd of 104 Grok 4.6 50.7%
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • 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 127th of 187 available · 37th of 61 at its price
BenchmarkMistral Small 4Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 11.3 130th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 9.9% 128th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 76.9% 104th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 111th of 169 available · 37th of 58 at its price
BenchmarkMistral Small 4Rank among availableBest available
UGI LeaderboardUGI: writing score · reported 40.3 81st of 124 Gemini 3.8 Flash 78.6
  • Arena (formerly LMArena): 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) 12th of 35 available · 4th of 8 at its price
BenchmarkMistral Small 4Rank among availableBest available
BulletBenchBulletBench Lightning 10+1: ladder Elo 571 5th of 18 Gemini 3.5 Flash-Lite 892
BulletBenchBulletBench Bullet 60s: ladder Elo 367 16th of 33 Gemini 3.8 Flash 1,068

Nearest alternatives

Against Mistral Small 4 at $0.26 blended, Intelligence Index 11.3. "Similar intelligence" means within 4 points or better.

Where to run it

3 hosts on OpenRouter at the standard service tier, with a median of $0.29 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Mistralnot stated$0.15$0.60$0.26
Mistralnot stated$0.17$0.66$0.29
Mistralnot stated$0.17$0.66$0.29

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.

Mistral Small 4MiMo-V2.6-Pro
most intelligent at $0.25–1 per million tokens
gpt-oss-20b
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
Mistral Large 4
most intelligent from the EU
Price per million tokens $0.26 $0.54$0.06$8.00$2.06
Tokens a second 176 432779660
Intelligence Index 11.3 46.310.057.638.4
Spring Prompt overall – ––8225
Rank among available models, by use case
Product listings – ––13th27th
Decks from an analysis – ––7th30th
User surveys – ––4th17th
Marketing planning – ––9th23rd
Agents and tool use 133rd of 159 23rd130th3rd37th
Professional work – ––3rd–
Reasoning and knowledge 127th of 187 13th132nd1st54th
Writing 111th of 169 23rd155th5th–
Sticking to the facts – 10th–3rd–
Speed under pressure 12th of 35 –––25th

Shaded figures are better than Mistral Small 4's. A dash means no result.

Where it has been measured

3rd most intelligent of the 15 models from developers based in the EU (all Mistral AI's). 38th most intelligent of the 61 models priced $0.25–1 per million tokens. Among models available today, in the bottom quarter for agents and tool use.

Every result

39 published results from 3 sources, each in the source's own units, with the configuration that produced it.

BulletBench · measured by Spring Prompt · 10 results
MeasureValueRankConfigurationDated
BulletBench Bullet 60s: cost per gameUS dollars, lower is better $0.0039 32 of 71 Mistral Small 4 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Bullet 60s: games lost on time% of games, lower is better 25.0% 32 of 71 Mistral Small 4 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Bullet 60s: invalid moves% of moves, lower is better 0.6% 68 of 71 Mistral Small 4 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Bullet 60s: ladder Eloladder Elo, higher is better 367
126–564
47 of 71 Mistral Small 4 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Bullet 60s: median move timemilliseconds, lower is better 0.6 s 16 of 71 Mistral Small 4 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: cost per gameUS dollars, lower is better $0.0041 31 of 48 Mistral Small 4 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: games lost on time% of games, lower is better 0.0% 1 of 48 Mistral Small 4 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: invalid moves% of moves, lower is better 1.0% 45 of 48 Mistral Small 4 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: ladder Eloladder Elo, higher is better 571
420–699
15 of 48 Mistral Small 4 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: median move timemilliseconds, lower is better 0.6 s 15 of 48 Mistral Small 4 (no reasoning)
none reasoning
1 Oct 2026

Not shown: Not your cost: prices are those charged on the run date.

Artificial Analysis · reported by Artificial Analysis · 23 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 26.6 140 of 187 Mistral Small 4 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 11.3 301 of 413 Mistral Small 4 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 9.0 336 of 413 Mistral Small 4 (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 76.9% 201 of 360 Mistral Small 4 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 57.1% 306 of 360 Mistral Small 4 (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 9.9% 282 of 419 Mistral Small 4 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 3.8% 389 of 419 Mistral Small 4 (no reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 48.2% 148 of 288 Mistral Small 4 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 32.8% 250 of 288 Mistral Small 4 (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 49.7% 283 of 407 Mistral Small 4 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 28.3% 344 of 407 Mistral Small 4 (no reasoning) 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 176 27 of 137 Mistral Small 4 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 166 29 of 137 Mistral Small 4 (no reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 38.8% 172 of 205 Mistral Small 4 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 21.0% 145 of 188 Mistral Small 4 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 Mistral Small 4 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 17.4% 161 of 282 Mistral Small 4 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 10.6% 198 of 282 Mistral Small 4 (no reasoning) 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 12.0 64 of 137 Mistral Small 4 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 0.57 9 of 137 Mistral Small 4 (no reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 4.9% 159 of 175 Mistral Small 4 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 41.2% 179 of 286 Mistral Small 4 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 18.4% 261 of 286 Mistral Small 4 (no reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

UGI Leaderboard · reported by UGI Leaderboard · 6 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 34.0% 278 of 379 Mistral Small 4 (high reasoning) 19 Mar 2026
UGI: requested-length error% off the requested word count, lower is better 22.0% 210 of 379 Mistral Small 4 (no reasoning) 19 Mar 2026
UGI: style adherencescore from 0 to 1, higher is better 0.31 319 of 379 Mistral Small 4 (high reasoning) 19 Mar 2026
UGI: style adherencescore from 0 to 1, higher is better 0.29 357 of 379 Mistral Small 4 (no reasoning) 19 Mar 2026
UGI: writing scorescore out of 100, higher is better 39.0 230 of 379 Mistral Small 4 (high reasoning) 19 Mar 2026
UGI: writing scorescore out of 100, higher is better 40.3 222 of 379 Mistral Small 4 (no reasoning) 19 Mar 2026

Not shown: Not other format limits such as character counts or bullet counts.

Embed a score badge

A badge for each of our benchmarks that ranked Mistral Small 4, from the current results. Paste the code into a page or README; it links back to the benchmark.

Mistral Small 4 is #15 of 45 on BulletBench (Lightning 10+1: 571), measured by Spring Prompt BulletBench · Lightning 10+1
<a href="https://springprompt.com/benchmarks/bulletbench?focus=mistral-mistral-small-2603"><img src="https://springprompt.com/badge/bulletbench/mistral-mistral-small-2603.svg" alt="Mistral Small 4 is #15 of 45 on BulletBench (Lightning 10+1: 571), measured by Spring Prompt" height="20"></a>

Will Mistral Small 4 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.