Models / Ministral 3 14B
Ministral 3 14B
Ministral 3 14B trails most of the field on what it has been measured on; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is Gemma 3 4B, at $0.04 per million tokens against $0.20.
Results 16 Nov 2026 · 22 results · 3 sources
Test Ministral 3 14B on your prompt → It runs beside the models you could use instead, with every answer checked and costed.
- Price per million tokens
- $0.20 in · $0.20 out
Mistral AI's list price, 10 Nov 2026 · compare prices$0.02 cached input · 50% off in batch - Speed
- 79 tokens a second; on its test prompt the answer starts after 0.5 s, thinking time included
Artificial Analysis, on its usual API - Intelligence Index
- 6.0
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
- 2 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.
| Among | Intelligence Index | Spring Prompt overall | Price, blended | Speed |
|---|---|---|---|---|
| Models available today | 174th of 185Claude Opus 5.5 | – | $0.20 blended, 18th percentilecheapest: Mistral Nemo | 44th of 65Nemotron 3.5 Super VL |
| Models priced under $0.25 per million tokens | 31st of 41Claude Haiku 5.5 | – | sets this group | 14th of 19Nemotron 3.5 Super VL |
| Models with similar intelligence | sets this group | – | $0.20 blended, 44th percentilecheapest: Gemma 3 4B | 10th of 14gpt-oss-20b |
| Models writing 50–100 tokens a second | 19th of 21Claude Opus 5.5 | – | $0.20 blended, 20th percentilecheapest: Granite 4.2 8B | sets this group |
| Models from developers based in the EUall Mistral AI's | 12th of 15Mistral Large 4 | – | $0.20 blended, 33rd percentilecheapest: Mistral Nemo | 5th of 6Ministral 3 3B |
| Open-weights models | 94th of 104MiMo-V2.6-Pro | – | $0.20 blended, 26th percentilecheapest: Mistral Nemo | 28th 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.
How good is it, and for what?
Each use case ranks the available models its benchmarks measured, then those priced under $0.25 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
- 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 | Ministral 3 14B | Rank among available | Best 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 | 9.7% | 91st of 107 | Claude Fable 5.1 91.4% |
| Artificial AnalysisArtificial Analysis: τ-bench banking · reported | 6.6% | 84th 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
- 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 | Ministral 3 14B | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported | 6.0 | 174th of 185 | Claude Opus 5.5 57.6 |
| Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported | 4.6% | 154th of 186 | Claude Opus 5.5 61.4% |
| Artificial AnalysisArtificial Analysis: GPQA Diamond · reported | 57.2% | 139th of 168 | GPT-6 Astra 96.3% |
WritingWhat people prefer in blind comparisons, and judged writing quality
| Benchmark | Ministral 3 14B | Rank among available | Best available |
|---|---|---|---|
| UGI LeaderboardUGI: writing score · reported | 31.4 | 102nd 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
| Benchmark | Ministral 3 14B | Rank among available | Best available |
|---|---|---|---|
| Vectara Hallucination LeaderboardVectara: hallucination rate · reported | 19.4% | 67th of 71 | GPT-5.4 nano 3.1% |
- 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
- Cheaper at similar intelligenceGemma 3 4B$0.04 blended · Intelligence Index 4.8Compare with Ministral 3 14B →
- Mistral AI's newer, at least as capable modelMistral Large 4$2.06 blended · Intelligence Index 38.4
Against Ministral 3 14B at $0.20 blended, Intelligence Index 6.0. "Similar intelligence" means within 4 points or better.
Where to run it
2 hosts on OpenRouter at the standard service tier, with a median of $0.21 blended per million tokens. Cheapest first.
| Host | Quantisation | Input | Output | Blended |
|---|---|---|---|---|
| Mistral | not stated | $0.20 | $0.20 | $0.20 |
| Mistral | not stated | $0.22 | $0.22 | $0.22 |
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.
| Ministral 3 14B | Claude Haiku 5.5 most intelligent at under $0.25 per million tokens | Gemma 3 4B cheapest with similar intelligence | gpt-oss-20b fastest with similar intelligence | Claude Opus 5.5 most intelligent available today | |
|---|---|---|---|---|---|
| Price per million tokens | $0.20 | $0.20 | $0.04 | $0.06 | $8.00 |
| Tokens a second | 79 | 240 | – | 277 | 96 |
| Intelligence Index | 6.0 | 43.4 | 4.8 | 10.0 | 57.6 |
| Spring Prompt overall | – | 40 | – | – | 82 |
| Rank among available models, by use case | |||||
| Product listings | – | 20th | – | – | 13th |
| Decks from an analysis | – | 18th | – | – | 7th |
| User surveys | – | 7th | – | – | 4th |
| Marketing planning | – | 30th | – | – | 9th |
| Agents and tool use | 134th of 159 | 28th | 158th | 130th | 3rd |
| Professional work | – | – | – | – | 3rd |
| Reasoning and knowledge | 157th of 187 | 25th | 181st | 132nd | 1st |
| Writing | 135th of 169 | – | 157th | 155th | 5th |
| Sticking to the facts | 133rd of 139 | – | 32nd | – | 3rd |
| Speed under pressure | – | 21st | – | – | – |
| Side by side → | Side by side → | Side by side → | |||
Shaded figures are better than Ministral 3 14B's. A dash means no result.
Where it has been measured
31st most intelligent of the 41 models priced under $0.25 per million tokens. Among models available today, in the bottom quarter for agents and tool use, reasoning and knowledge, writing, and sticking to the facts.
- Artificial Analysis14 results
- UGI Leaderboard6 results
- Vectara Hallucination Leaderboard2 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
- Vending-Bench 2Not measured
Every result
22 published results from 3 sources, each in the source's own units, with the configuration that produced it.
Artificial Analysis · reported by Artificial Analysis · 14 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better | 14.4 | 167 of 187 | Ministral 3 14B | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 6.0 | 396 of 413 | Ministral 3 14B | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 57.2% | 305 of 360 | Ministral 3 14B | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 4.6% | 356 of 419 | Ministral 3 14B | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 32.0% | 255 of 288 | Ministral 3 14B | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 26.3% | 348 of 407 | Ministral 3 14B | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 79.2 | 84 of 137 | Ministral 3 14B | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 23.8% | 200 of 205 | Ministral 3 14B | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better | 9.7% | 161 of 188 | Ministral 3 14B | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 0.0% | 152 of 204 | Ministral 3 14B | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 4.5% | 237 of 282 | Ministral 3 14B | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 0.52 | 7 of 137 | Ministral 3 14B | 20 Oct 2026 |
| Artificial Analysis: τ-bench banking% of tasks, higher is better | 6.6% | 144 of 175 | Ministral 3 14B | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 27.2% | 225 of 286 | Ministral 3 14B | 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 | 24.0% | 225 of 379 | Ministral 3 14B | 3 Dec 2025 |
| UGI: requested-length error% off the requested word count, lower is better | 58.0% | 328 of 379 | Ministral 3 14B (think-prefill reasoning) | 3 Dec 2025 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.32 | 286 of 379 | Ministral 3 14B | 3 Dec 2025 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.31 | 314 of 379 | Ministral 3 14B (think-prefill reasoning) | 3 Dec 2025 |
| UGI: writing scorescore out of 100, higher is better | 31.4 | 274 of 379 | Ministral 3 14B | 3 Dec 2025 |
| UGI: writing scorescore out of 100, higher is better | 25.7 | 307 of 379 | Ministral 3 14B (think-prefill reasoning) | 3 Dec 2025 |
Not shown: Not other format limits such as character counts or bullet counts.
Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Vectara: answer rate% of documents, higher is better | 99.6% | 48 of 108 | Ministral 3 14B | 22 Sep 2026 |
| Vectara: hallucination rate% of summaries, lower is better | 19.4% | 101 of 108 | Ministral 3 14B | 22 Sep 2026 |
Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.
Will Ministral 3 14B 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.