As of October 20, 2026, Mistral Large 4 ranks #32 of 213 models overall with 38.4 on the Artificial Analysis Intelligence Index. Its strongest category is math, where it ranks #19 of 116. Mistral Large 4 costs $0.68 per million input tokens and $2.09 per million output tokens. It was released on October 6, 2026.
Its output price ranks 200 of 349 priced models, counting from the cheapest.
Listed on OpenRouter October 6, 2026, 14 days before our data. Results so far on 80 of 190 public boards; this page updates every day as boards publish.
Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...
mistralai/mistral-large-4-0 The tick on a coding bar is the median of every model measured on it. Outside coding, the place is this model's rank on that board. A board that never ran the model says so.
Measured in 4 of 6 categories. A place counts only the models measured on that board.
The index averages only the coding benchmarks that have a result; the others are skipped, never filled in. How it is weighted
Not measured on SWE-bench Lite, SWE-bench (full test set), SWE-bench Multimodal, SWE-bench Multilingual, AA Coding Index, LiveCodeBench (Vals AI), SWE-bench Verified (Vals AI), ProgramBench (Vals AI), Terminal-Bench 2.1 (Vals AI), SkillsBench (Vals AI), CyberBench (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, DeepSWE, FrontierSWE, GSO-Bench, WeirdML, MirrorCode, Cybench, LMArena WebDev: from an image
Not measured on AA Agentic Index, Design Arena: agents building web apps, Design Arena: agents building full-stack apps, Design Arena: agents building mobile apps, Design Arena: agents building Android apps, Design Arena: agents building Godot games, Design Arena: agents building games, Design Arena: HTML slides, Design Arena: PowerPoint slides, Design Arena: spreadsheets, SREBench (Vals AI), Terminal-Bench-Science (Vals AI), Vals Science Index, Time Horizon Index (Vals AI), CUA-bench (Vals AI), Robo-bench (Vals AI), τ²-Bench Telecom, APEX-Agents, METR time horizons, Remote Labor Index, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, PostTrainBench, TheAgentCompany, OSWorld, SpireClimb, Vending-Bench 2, LMArena Search
Not measured on GPQA Diamond, MMMU Pro (Vals AI), GPQA Diamond (Artificial Analysis run), ARC-AGI, ARC-AGI-2, Humanity's Last Exam, SimpleBench, EBR-bench, VPCT, BIG-Bench Hard, LMArena Vision: homework
Not measured on AIME, MATH 500 (Vals AI), MGSM (Vals AI), AA Math Index, AIME 2025 (Artificial Analysis run), MATH level 5, GSM8K
Not measured on MMLU Pro, LegalBench (Vals AI), CaseLaw (Vals AI), CorpFin (Vals AI), TaxEval (Vals AI), MortgageTax (Vals AI), MedQA (Vals AI), MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on Vals Index, Public Benefits Bench (Vals AI), SAGE (Vals AI), Vals Multimodal Index, IFBench, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, LMArena Text: German, LMArena Text: Japanese, LMArena Text: Korean, LMArena Text: Polish, LMArena Vision: Chinese, LMArena Vision: humor, LMArena Vision: captioning, LMArena Vision: recognizing things, LMArena Vision: creative writing, LMArena Document
Not measured on Design Arena: images, Design Arena: graphic design, Design Arena: logos, LMArena Text to Image, LMArena Image Edit
Public boards shown as published (Vals AI, Artificial Analysis, Design Arena) and kept out of the coding index. Each links to its source on the benchmark page.
| Benchmark | Result | Index weight |
|---|---|---|
| Aider polyglotCoding | Not measured | 35% |
| SWE-bench VerifiedCoding | Not measured | 30% |
| SWE-bench LiteCoding | Not measured | Not in index |
| SWE-bench (full test set)Coding | Not measured | Not in index |
| SWE-bench MultimodalCoding | Not measured | Not in index |
| SWE-bench MultilingualCoding | Not measured | Not in index |
| LiveBench codingCoding | 60.0% | 20% |
| LMArena WebDevCoding | 1543 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | Not measured | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | Not measured | Not in index |
| AA Intelligence IndexIntelligence | 38.4 | Not in index |
| AA Coding IndexCoding | Not measured | Not in index |
| AA Agentic IndexAgentic work | Not measured | Not in index |
| Design Arena: websitesWeb design | 1258 | Not in index |
| Design Arena: UI componentsWeb design | 1275 | Not in index |
| Design Arena: game devWeb design | 1226 | Not in index |
| Design Arena: data vizWeb design | 1274 | Not in index |
| Design Arena: 3DWeb design | 1253 | Not in index |
| Design Arena: all code categoriesWeb design | 1259 | Not in index |
| Design Arena: SVGWeb design | 1232 | Not in index |
| Design Arena: ASCII artWeb design | 1202 | Not in index |
| Design Arena: agents building web appsAgentic work | Not measured | Not in index |
| Design Arena: agents building full-stack appsAgentic work | Not measured | Not in index |
| Design Arena: agents building mobile appsAgentic work | Not measured | Not in index |
| Design Arena: agents building Android appsAgentic work | Not measured | Not in index |
| Design Arena: agents building Godot gamesAgentic work | Not measured | Not in index |
| Design Arena: agents building gamesAgentic work | Not measured | Not in index |
| Design Arena: HTML slidesAgentic work | Not measured | Not in index |
| Design Arena: PowerPoint slidesAgentic work | Not measured | Not in index |
| Design Arena: spreadsheetsAgentic work | Not measured | Not in index |
| Design Arena: imagesImage generation | Not measured | Not in index |
| Design Arena: graphic designImage generation | Not measured | Not in index |
| Design Arena: logosImage generation | Not measured | Not in index |
| LiveBench reasoningReasoning | 83.9% | Not in index |
| LiveBench data analysisGeneral | 76.5% | Not in index |
| LiveBench researchAgentic work | 28.1% | Not in index |
| LiveBench browserAgentic work | 8.0% | Not in index |
| LiveBench long agenticAgentic work | 11.8% | Not in index |
| LiveBench designWeb design | 65.6% | Not in index |
| LiveCodeBench (Vals AI)Coding | Not measured | Not in index |
| SWE-bench Verified (Vals AI)Coding | Not measured | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 27.8% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 78.4% | Not in index |
| Code migration (Vals AI)Coding | 30.6% | Not in index |
| ProgramBench (Vals AI)Coding | Not measured | Not in index |
| SREBench (Vals AI)Agentic work | Not measured | Not in index |
| IOI (Vals AI)Coding | 45.3% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | Not measured | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | 33.1% | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | 14.3% | Not in index |
| SkillsBench (Vals AI)Coding | Not measured | Not in index |
| CyberBench (Vals AI)Coding | Not measured | Not in index |
| Finance Agent (Vals AI)Agentic work | 54.7% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 30.4% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 31.7% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | 17.5% | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 56.2% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | 67.0% | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | Not measured | Not in index |
| Vals Science IndexAgentic work | Not measured | Not in index |
| Time Horizon Index (Vals AI)Agentic work | Not measured | Not in index |
| CUA-bench (Vals AI)Agentic work | Not measured | Not in index |
| Robo-bench (Vals AI)Agentic work | Not measured | Not in index |
| Public Benefits Bench (Vals AI)General | Not measured | Not in index |
| MysteryMechanism (Vals AI)Reasoning | 12.2% | Not in index |
| MMMU Pro (Vals AI)Reasoning | Not measured | Not in index |
| MATH 500 (Vals AI)Math | Not measured | Not in index |
| MGSM (Vals AI)Math | Not measured | Not in index |
| SAGE (Vals AI)General | Not measured | Not in index |
| LegalBench (Vals AI)Knowledge | Not measured | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | Not measured | Not in index |
| TaxEval (Vals AI)Knowledge | Not measured | Not in index |
| MortgageTax (Vals AI)Knowledge | Not measured | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 40.7% | Not in index |
| MedScribe (Vals AI)General | 80.4% | Not in index |
| Vals Multimodal IndexGeneral | Not measured | Not in index |
| AA Math IndexMath | Not measured | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | Not measured | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 35.0% | Not in index |
| MMLU Pro (Artificial Analysis run)Knowledge | Not measured | Not in index |
| LiveCodeBench (Artificial Analysis run)Coding | Not measured | Not in index |
| SciCodeCoding | 54.2% | Not in index |
| Terminal-Bench Hard (Artificial Analysis run)Coding | Not measured | Not in index |
| IFBenchGeneral | Not measured | Not in index |
| Long context reasoning (AA-LCR)General | 81.3% | Not in index |
| τ²-Bench TelecomAgentic work | Not measured | Not in index |
| AIME 2025 (Artificial Analysis run)Math | Not measured | Not in index |
| Terminal-BenchCoding | Not measured | Not in index |
| DeepSWECoding | Not measured | Not in index |
| FrontierCodeCoding | 39.4% | Not in index |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | Not measured | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | Not measured | Not in index |
| METR time horizonsAgentic work | Not measured | Not in index |
| Remote Labor IndexAgentic work | Not measured | Not in index |
| GDPvalAgentic work | Not measured | Not in index |
| OSWorld 2.0Agentic work | Not measured | Not in index |
| BALROGAgentic work | Not measured | Not in index |
| DeepResearch BenchAgentic work | Not measured | Not in index |
| PostTrainBenchAgentic work | Not measured | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 88.1% | Not in index |
| ARC-AGIReasoning | Not measured | Not in index |
| ARC-AGI-2Reasoning | Not measured | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | Not measured | Not in index |
| Chess puzzlesReasoning | 33.0% | Not in index |
| Mystery game puzzlesReasoning | 17.0% | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 98.3% | Not in index |
| FrontierMath, tiers 1 to 3Math | 58.6% | Not in index |
| FrontierMath, tier 4Math | 26.8% | Not in index |
| ProofBenchMath | 10.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 20.0% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 88.2% | Not in index |
| LMCAGeneral | 35.8% | Not in index |
| Fiction.LiveBenchGeneral | Not measured | Not in index |
| Creative writing (Lech Mazur)General | Not measured | Not in index |
| CL-benchGeneral | Not measured | Not in index |
| Surface Evolver BenchGeneral | 28.1% | Not in index |
| Furniture assemblyGeneral | 20.8% | Not in index |
| ExploitBenchGeneral | Not measured | Not in index |
| CybenchCoding | Not measured | Not in index |
| TheAgentCompanyAgentic work | Not measured | Not in index |
| OSWorldAgentic work | Not measured | Not in index |
| SpireClimbAgentic work | Not measured | Not in index |
| VPCTReasoning | Not measured | Not in index |
| BIG-Bench HardReasoning | Not measured | Not in index |
| AI2 Reasoning ChallengeKnowledge | Not measured | Not in index |
| HellaSwagGeneral | Not measured | Not in index |
| WinoGrandeGeneral | Not measured | Not in index |
| PIQAGeneral | Not measured | Not in index |
| CL-bench LifeGeneral | Not measured | Not in index |
| ALE-BenchCoding | 1213.2 | Not in index |
| Vending-Bench 2Agentic work | Not measured | Not in index |
| Epoch Capabilities IndexIntelligence | 146.9 | Not in index |
| LMArena TextGeneral | 1430 | Not in index |
| LMArena Text: codingCoding | 1481 | Not in index |
| LMArena Text: hard promptsReasoning | 1444 | Not in index |
| LMArena Text: mathMath | 1469 | Not in index |
| LMArena Text: instruction followingGeneral | 1421 | Not in index |
| LMArena Text: creative writingGeneral | 1362 | Not in index |
| LMArena VisionGeneral | 1272 | Not in index |
| LMArena Text: EnglishGeneral | 1432 | Not in index |
| LMArena Text: non-EnglishGeneral | 1420 | Not in index |
| LMArena Text: ChineseGeneral | 1492 | Not in index |
| LMArena Text: GermanGeneral | Not measured | Not in index |
| LMArena Text: JapaneseGeneral | Not measured | Not in index |
| LMArena Text: KoreanGeneral | Not measured | Not in index |
| LMArena Text: FrenchGeneral | 1494 | Not in index |
| LMArena Text: SpanishGeneral | 1443 | Not in index |
| LMArena Text: RussianGeneral | 1422 | Not in index |
| LMArena Text: PolishGeneral | Not measured | Not in index |
| LMArena Text: multi-turnGeneral | 1437 | Not in index |
| LMArena Text: longer queriesGeneral | 1427 | Not in index |
| LMArena Text: expertReasoning | 1442 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1442 | Not in index |
| LMArena Text: software and ITCoding | 1468 | Not in index |
| LMArena Text: mathematical workMath | 1461 | Not in index |
| LMArena Text: scienceKnowledge | 1444 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1423 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1422 | Not in index |
| LMArena Text: business and financeKnowledge | 1436 | Not in index |
| LMArena Text: writing and languageGeneral | 1383 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1376 | Not in index |
| LMArena WebDev: ReactCoding | 1559 | Not in index |
| LMArena WebDev: HTMLCoding | 1487 | Not in index |
| LMArena WebDev: from an imageCoding | Not measured | Not in index |
| LMArena Vision: EnglishGeneral | 1283 | Not in index |
| LMArena Vision: ChineseGeneral | Not measured | Not in index |
| LMArena Vision: reading textGeneral | 1284 | Not in index |
| LMArena Vision: diagramsReasoning | 1288 | Not in index |
| LMArena Vision: homeworkReasoning | Not measured | Not in index |
| LMArena Vision: humorGeneral | Not measured | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | Not measured | Not in index |
| LMArena SearchAgentic work | Not measured | Not in index |
| LMArena DocumentGeneral | Not measured | Not in index |
| LMArena Text to ImageImage generation | Not measured | Not in index |
| LMArena Image EditImage generation | Not measured | Not in index |
A list price says what a token costs. The cost per solved task says what a working answer costs, which is the number that decides.
Neither board that publishes what a SWE-bench Verified attempt costs, Vals AI and swebench.com, has run this model. We leave the number out rather than estimate it.
LiveBench, on its own coding tasks, publishes what one task cost this model: $0.983, at a score of 60.0%. LiveBench counts that as $1.638 per successful task. Different tasks from SWE-bench, so it is not our number and does not enter its ranking. LiveBench coding
Beside a result, many boards publish what the run cost, how long it took, the tokens it spent or the votes behind a rating. Each figure as its board printed it, one board per row.
| Board | Result | What the run cost | Also published |
|---|---|---|---|
| LiveBench coding | 60.0% | $0.9826 per task | Output tokens per task 45,501 |
| LiveBench reasoning | 83.9% | $0.119 per task | Output tokens per task 56,566 |
| LiveBench data analysis | 76.5% | $0.1337 per task | Output tokens per task 62,776 |
| LiveBench research | 28.1% | $2.3272 per task | Output tokens per task 229,696 |
| LiveBench browser | 8.0% | $0.4506 per task | Output tokens per task 6,551 |
| LiveBench long agentic | 11.8% | $9.5557 per task | Output tokens per task 508,413 |
| LiveBench design | 65.6% | $0.389 per task | Output tokens per task 123,574 |
| Terminal-Bench 4 (Vals AI) | 27.8% | $10.25 per test | Duration, as printed 1h 40m |
| Vibe Code Bench (Vals AI) | 78.4% | $39.46 per test | Duration, as printed 2h 53m |
| Code migration (Vals AI) | 30.6% | $47.89 per test | Duration, as printed 4h 51m |
| IOI (Vals AI) | 45.3% | $5.39 per test | Duration, as printed 1h 24m |
| SWE-bench Multimodal (Vals AI) | 33.1% | $5.14 per test | Duration, as printed 27m 27s |
| Vibe Code Bench 1-100 (Vals AI) | 14.3% | $6.75 per test | Duration, as printed 1h 00m |
|---|---|---|---|
| Finance Agent (Vals AI) | 54.7% | $1.20 per test | Duration, as printed 26m 02s |
| Tax Agent Bench (Vals AI) | 30.4% | $2.72 per test | Duration, as printed 57m 18s |
| Legal Research Bench (Vals AI) | 31.7% | $5.33 per test | Duration, as printed 1h 33m |
| Harvey's Legal Agent Benchmark (Vals AI) | 17.5% | $4.18 per test | Duration, as printed 58m 04s |
| Excel Modeling Benchmark (Vals AI) | 56.2% | $4.84 per test | Duration, as printed 1h 22m |
| BioMysteryBench (Vals AI) | 67.0% | $2.07 per test | Duration, as printed 25m 32s |
| MysteryMechanism (Vals AI) | 12.2% | $2.10 per test | Duration, as printed 35m 37s |
| ProofBench | 10.0% | $0.6424 per test | Time per proof 20m 59s |
| Surface Evolver Bench | 28.1% | $6.0172 of the run | Pass rate 18.8% · Tokens for the run 5.7M |
| ALE-Bench | 1213.2 | $0.4569 per problem | Tokens per problem 121,609 |
| LMArena WebDev | 1543 Elo | Not published | Votes 2,832 · Interval (±) ±12.3 |
| Design Arena: websites | 1258 Elo | Not published | Battles 3,010 |
| Design Arena: UI components | 1275 Elo | Not published | Battles 416 |
| Design Arena: game dev | 1226 Elo | Not published | Battles 1,406 |
| Design Arena: data viz | 1274 Elo | Not published | Battles 404 |
| Design Arena: 3D | 1253 Elo | Not published | Battles 1,341 |
| Design Arena: all code categories | 1259 Elo | Not published | Battles 5,988 |
| Design Arena: SVG | 1232 Elo | Not published | Battles 939 |
| Design Arena: ASCII art | 1202 Elo | Not published | Battles 161 |
| MedCode (Vals AI) | 40.7% | Not published | Latency, as printed 1m 09s |
| MedScribe (Vals AI) | 80.4% | Not published | Latency, as printed 2m 05s |
| LMArena Text | 1430 Elo | Not published | Votes 7,451 · Interval (±) ±7.2 |
| LMArena Text: coding | 1481 Elo | Not published | Votes 1,685 · Interval (±) ±14.3 |
| LMArena Text: hard prompts | 1444 Elo | Not published | Votes 4,626 · Interval (±) ±9.0 |
| LMArena Text: math | 1469 Elo | Not published | Votes 377 · Interval (±) ±29.1 |
| LMArena Text: instruction following | 1421 Elo | Not published | Votes 2,579 · Interval (±) ±11.8 |
| LMArena Text: creative writing | 1362 Elo | Not published | Votes 1,694 · Interval (±) ±15.0 |
| LMArena Vision | 1272 Elo | Not published | Votes 1,008 · Interval (±) ±19.2 |
| LMArena Text: English | 1432 Elo | Not published | Votes 2,970 · Interval (±) ±11.0 |
| LMArena Text: non-English | 1420 Elo | Not published | Votes 4,479 · Interval (±) ±9.1 |
| LMArena Text: Chinese | 1492 Elo | Not published | Votes 658 · Interval (±) ±23.0 |
| LMArena Text: French | 1494 Elo | Not published | Votes 286 · Interval (±) ±36.2 |
| LMArena Text: Spanish | 1443 Elo | Not published | Votes 249 · Interval (±) ±37.7 |
| LMArena Text: Russian | 1422 Elo | Not published | Votes 953 · Interval (±) ±18.7 |
| LMArena Text: multi-turn | 1437 Elo | Not published | Votes 1,069 · Interval (±) ±18.3 |
| LMArena Text: longer queries | 1427 Elo | Not published | Votes 3,141 · Interval (±) ±11.0 |
| LMArena Text: expert | 1442 Elo | Not published | Votes 754 · Interval (±) ±21.1 |
| LMArena Text: hard prompts in English | 1442 Elo | Not published | Votes 1,858 · Interval (±) ±13.9 |
| LMArena Text: software and IT | 1468 Elo | Not published | Votes 2,593 · Interval (±) ±11.5 |
| LMArena Text: mathematical work | 1461 Elo | Not published | Votes 393 · Interval (±) ±28.7 |
| LMArena Text: science | 1444 Elo | Not published | Votes 1,232 · Interval (±) ±16.9 |
| LMArena Text: medicine and healthcare | 1423 Elo | Not published | Votes 523 · Interval (±) ±25.8 |
| LMArena Text: legal and government | 1422 Elo | Not published | Votes 597 · Interval (±) ±23.9 |
| LMArena Text: business and finance | 1436 Elo | Not published | Votes 1,233 · Interval (±) ±16.5 |
| LMArena Text: writing and language | 1383 Elo | Not published | Votes 2,139 · Interval (±) ±13.1 |
| LMArena Text: entertainment and media | 1376 Elo | Not published | Votes 1,960 · Interval (±) ±14.0 |
| LMArena WebDev: React | 1559 Elo | Not published | Votes 1,783 · Interval (±) ±15.5 |
| LMArena WebDev: HTML | 1487 Elo | Not published | Votes 374 · Interval (±) ±35.3 |
| LMArena Vision: English | 1283 Elo | Not published | Votes 355 · Interval (±) ±31.5 |
| LMArena Vision: reading text | 1284 Elo | Not published | Votes 671 · Interval (±) ±23.1 |
| LMArena Vision: diagrams | 1288 Elo | Not published | Votes 243 · Interval (±) ±37.3 |