As of October 20, 2026, Google Gemma 4 31B ranks #123 of 213 models overall with 14.7 on the Artificial Analysis Intelligence Index. Its strongest category is reasoning, where it ranks #126 of 203. Google Gemma 4 31B costs $0.20 per million input tokens and $0.40 per million output tokens. It was released on April 2, 2026.
Its output price ranks 71 of 349 priced models, counting from the cheapest.
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
google/gemma-4-31b-it 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, LiveCodeBench (Vals AI), SWE-bench Verified (Vals AI), Terminal-Bench 4 (Vals AI), Vibe Code Bench (Vals AI), Code migration (Vals AI), ProgramBench (Vals AI), IOI (Vals AI), Terminal-Bench 2.1 (Vals AI), SWE-bench Multimodal (Vals AI), Vibe Code Bench 1-100 (Vals AI), SkillsBench (Vals AI), CyberBench (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench, DeepSWE, FrontierCode, FrontierSWE, GSO-Bench, MirrorCode, Cybench, LMArena WebDev: from an image
Not measured on 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), Finance Agent (Vals AI), Tax Agent Bench (Vals AI), Legal Research Bench (Vals AI), Harvey's Legal Agent Benchmark (Vals AI), Excel Modeling Benchmark (Vals AI), BioMysteryBench (Vals AI), Terminal-Bench-Science (Vals AI), Vals Science Index, Time Horizon Index (Vals AI), CUA-bench (Vals AI), Robo-bench (Vals AI), 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, MysteryMechanism (Vals AI), MMMU Pro (Vals AI), ARC-AGI, ARC-AGI-2, Humanity's Last Exam, SimpleBench, Chess puzzles, Mystery game puzzles, EBR-bench, VPCT, BIG-Bench Hard
Not measured on AIME, MATH 500 (Vals AI), MGSM (Vals AI), AA Math Index, AIME 2025 (Artificial Analysis run), FrontierMath, tiers 1 to 3, FrontierMath, tier 4, ProofBench, MATH level 5, GSM8K
Not measured on MMLU Pro, LegalBench (Vals AI), CorpFin (Vals AI), TaxEval (Vals AI), MedQA (Vals AI), MedCode (Vals AI), MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on Design Arena: websites, Design Arena: UI components, Design Arena: game dev, Design Arena: data viz, Design Arena: 3D, Design Arena: all code categories, Design Arena: SVG, Design Arena: ASCII art
Not measured on Vals Index, Public Benefits Bench (Vals AI), MedScribe (Vals AI), Vals Multimodal Index, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, Furniture assembly, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, LMArena Text: German, LMArena Text: Japanese, LMArena Text: Korean
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 | 49.0% | 20% |
| LMArena WebDevCoding | 1367 | 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 | 14.7 | Not in index |
| AA Coding IndexCoding | 43.4 | Not in index |
| AA Agentic IndexAgentic work | 4.2 | Not in index |
| Design Arena: websitesWeb design | Not measured | Not in index |
| Design Arena: UI componentsWeb design | Not measured | Not in index |
| Design Arena: game devWeb design | Not measured | Not in index |
| Design Arena: data vizWeb design | Not measured | Not in index |
| Design Arena: 3DWeb design | Not measured | Not in index |
| Design Arena: all code categoriesWeb design | Not measured | Not in index |
| Design Arena: SVGWeb design | Not measured | Not in index |
| Design Arena: ASCII artWeb design | Not measured | 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 | 68.3% | Not in index |
| LiveBench data analysisGeneral | 53.3% | Not in index |
| LiveBench researchAgentic work | 44.4% | Not in index |
| LiveBench browserAgentic work | 4.0% | Not in index |
| LiveBench long agenticAgentic work | 13.3% | Not in index |
| LiveBench designWeb design | 58.4% | 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 | Not measured | Not in index |
| Vibe Code Bench (Vals AI)Coding | Not measured | Not in index |
| Code migration (Vals AI)Coding | Not measured | 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 | Not measured | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | Not measured | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | Not measured | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | Not measured | 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 | Not measured | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | Not measured | Not in index |
| Legal Research Bench (Vals AI)Agentic work | Not measured | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| BioMysteryBench (Vals AI)Agentic work | Not measured | 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 | Not measured | 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 | 55.0% | Not in index |
| LegalBench (Vals AI)Knowledge | Not measured | Not in index |
| CaseLaw (Vals AI)Knowledge | 52.6% | 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 | 61.4% | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | Not measured | Not in index |
| MedScribe (Vals AI)General | Not measured | 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 | 85.7% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 23.6% | 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 | 45.5% | Not in index |
| Terminal-Bench Hard (Artificial Analysis run)Coding | 36.4% | Not in index |
| IFBenchGeneral | 75.6% | Not in index |
| Long context reasoning (AA-LCR)General | 69.7% | Not in index |
| τ²-Bench TelecomAgentic work | 65.5% | 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 | Not measured | Not in index |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | 52.3% | 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 | 75.8% | 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 | Not measured | Not in index |
| Mystery game puzzlesReasoning | Not measured | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 73.3% | Not in index |
| FrontierMath, tiers 1 to 3Math | Not measured | Not in index |
| FrontierMath, tier 4Math | Not measured | Not in index |
| ProofBenchMath | Not measured | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 10.4% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 82.7% | Not in index |
| LMCAGeneral | 39.3% | 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 | 30.6% | Not in index |
| Furniture assemblyGeneral | Not measured | 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 | 925.5 | Not in index |
| Vending-Bench 2Agentic work | Not measured | Not in index |
| Epoch Capabilities IndexIntelligence | 142.9 | Not in index |
| LMArena TextGeneral | 1443 | Not in index |
| LMArena Text: codingCoding | 1459 | Not in index |
| LMArena Text: hard promptsReasoning | 1448 | Not in index |
| LMArena Text: mathMath | 1464 | Not in index |
| LMArena Text: instruction followingGeneral | 1433 | Not in index |
| LMArena Text: creative writingGeneral | 1415 | Not in index |
| LMArena VisionGeneral | 1276 | Not in index |
| LMArena Text: EnglishGeneral | 1451 | Not in index |
| LMArena Text: non-EnglishGeneral | 1431 | Not in index |
| LMArena Text: ChineseGeneral | 1475 | 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 | 1435 | Not in index |
| LMArena Text: SpanishGeneral | 1443 | Not in index |
| LMArena Text: RussianGeneral | 1461 | Not in index |
| LMArena Text: PolishGeneral | 1431 | Not in index |
| LMArena Text: multi-turnGeneral | 1452 | Not in index |
| LMArena Text: longer queriesGeneral | 1446 | Not in index |
| LMArena Text: expertReasoning | 1464 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1456 | Not in index |
| LMArena Text: software and ITCoding | 1463 | Not in index |
| LMArena Text: mathematical workMath | 1465 | Not in index |
| LMArena Text: scienceKnowledge | 1457 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1451 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1439 | Not in index |
| LMArena Text: business and financeKnowledge | 1431 | Not in index |
| LMArena Text: writing and languageGeneral | 1431 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1404 | Not in index |
| LMArena WebDev: ReactCoding | 1359 | Not in index |
| LMArena WebDev: HTMLCoding | 1380 | Not in index |
| LMArena WebDev: from an imageCoding | Not measured | Not in index |
| LMArena Vision: EnglishGeneral | 1271 | Not in index |
| LMArena Vision: ChineseGeneral | 1326 | Not in index |
| LMArena Vision: reading textGeneral | 1282 | Not in index |
| LMArena Vision: diagramsReasoning | 1283 | Not in index |
| LMArena Vision: homeworkReasoning | 1310 | Not in index |
| LMArena Vision: humorGeneral | 1280 | Not in index |
| LMArena Vision: captioningGeneral | 1218 | Not in index |
| LMArena Vision: recognizing thingsGeneral | 1226 | Not in index |
| LMArena Vision: creative writingGeneral | 1285 | Not in index |
| LMArena SearchAgentic work | Not measured | Not in index |
| LMArena DocumentGeneral | 1425 | 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: $0.233, at a score of 49.0%. LiveBench counts that as $0.475 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 | 49.0% | $0.2326 per task | Output tokens per task 11,719 |
| LiveBench reasoning | 68.3% | $0.0038 per task | Output tokens per task 9,019 |
| LiveBench data analysis | 53.3% | $0.0046 per task | Output tokens per task 9,487 |
| LiveBench research | 44.4% | $0.0384 per task | Output tokens per task 10,393 |
| LiveBench browser | 4.0% | $0.2541 per task | Output tokens per task 100,134 |
| LiveBench long agentic | 13.3% | $0.9887 per task | Output tokens per task 42,056 |
| LiveBench design | 58.4% | $0.0148 per task | Output tokens per task 9,942 |
| WeirdML | 52.3% | $0.0133 per run | Median lines of code 126 |
| Surface Evolver Bench | 30.6% | $0.2156 of the run | Pass rate 6.3% · Tokens for the run 1.4M |
| ALE-Bench | 925.5 | $0.0047 per problem | Tokens per problem 14,037 |
| LMArena WebDev | 1367 Elo | Not published | Votes 14,666 · Interval (±) ±6.2 |
| SAGE (Vals AI) | 55.0% | Not published | Latency, as printed 1m 33s |
| CaseLaw (Vals AI) | 52.6% | Not published | Latency, as printed 29 s |
|---|---|---|---|
| MortgageTax (Vals AI) | 61.4% | Not published | Latency, as printed 42 s |
| LMArena Text | 1443 Elo | Not published | Votes 6,147 · Interval (±) ±7.4 |
| LMArena Text: coding | 1459 Elo | Not published | Votes 1,418 · Interval (±) ±15.0 |
| LMArena Text: hard prompts | 1448 Elo | Not published | Votes 3,573 · Interval (±) ±9.6 |
| LMArena Text: math | 1464 Elo | Not published | Votes 430 · Interval (±) ±26.6 |
| LMArena Text: instruction following | 1433 Elo | Not published | Votes 1,803 · Interval (±) ±13.6 |
| LMArena Text: creative writing | 1415 Elo | Not published | Votes 974 · Interval (±) ±18.6 |
| LMArena Vision | 1276 Elo | Not published | Votes 40,219 · Interval (±) ±5.7 |
| LMArena Text: English | 1451 Elo | Not published | Votes 2,332 · Interval (±) ±11.8 |
| LMArena Text: non-English | 1431 Elo | Not published | Votes 3,815 · Interval (±) ±9.3 |
| LMArena Text: Chinese | 1475 Elo | Not published | Votes 522 · Interval (±) ±24.9 |
| LMArena Text: French | 1435 Elo | Not published | Votes 269 · Interval (±) ±34.8 |
| LMArena Text: Spanish | 1443 Elo | Not published | Votes 253 · Interval (±) ±35.4 |
| LMArena Text: Russian | 1461 Elo | Not published | Votes 827 · Interval (±) ±19.6 |
| LMArena Text: Polish | 1431 Elo | Not published | Votes 203 · Interval (±) ±37.5 |
| LMArena Text: multi-turn | 1452 Elo | Not published | Votes 1,124 · Interval (±) ±17.2 |
| LMArena Text: longer queries | 1446 Elo | Not published | Votes 1,801 · Interval (±) ±13.4 |
| LMArena Text: expert | 1464 Elo | Not published | Votes 501 · Interval (±) ±24.8 |
| LMArena Text: hard prompts in English | 1456 Elo | Not published | Votes 1,332 · Interval (±) ±15.7 |
| LMArena Text: software and IT | 1463 Elo | Not published | Votes 2,224 · Interval (±) ±12.0 |
| LMArena Text: mathematical work | 1465 Elo | Not published | Votes 345 · Interval (±) ±29.2 |
| LMArena Text: science | 1457 Elo | Not published | Votes 933 · Interval (±) ±18.8 |
| LMArena Text: medicine and healthcare | 1451 Elo | Not published | Votes 422 · Interval (±) ±27.9 |
| LMArena Text: legal and government | 1439 Elo | Not published | Votes 452 · Interval (±) ±26.1 |
| LMArena Text: business and finance | 1431 Elo | Not published | Votes 1,180 · Interval (±) ±16.6 |
| LMArena Text: writing and language | 1431 Elo | Not published | Votes 1,429 · Interval (±) ±15.3 |
| LMArena Text: entertainment and media | 1404 Elo | Not published | Votes 1,095 · Interval (±) ±17.5 |
| LMArena WebDev: React | 1359 Elo | Not published | Votes 11,333 · Interval (±) ±6.9 |
| LMArena WebDev: HTML | 1380 Elo | Not published | Votes 2,025 · Interval (±) ±14.7 |
| LMArena Vision: English | 1271 Elo | Not published | Votes 15,807 · Interval (±) ±7.7 |
| LMArena Vision: Chinese | 1326 Elo | Not published | Votes 2,734 · Interval (±) ±14.1 |
| LMArena Vision: reading text | 1282 Elo | Not published | Votes 28,054 · Interval (±) ±5.7 |
| LMArena Vision: diagrams | 1283 Elo | Not published | Votes 10,238 · Interval (±) ±7.7 |
| LMArena Vision: homework | 1310 Elo | Not published | Votes 6,435 · Interval (±) ±8.7 |
| LMArena Vision: humor | 1280 Elo | Not published | Votes 1,659 · Interval (±) ±14.8 |
| LMArena Vision: captioning | 1218 Elo | Not published | Votes 106 · Interval (±) ±54.1 |
| LMArena Vision: recognizing things | 1226 Elo | Not published | Votes 359 · Interval (±) ±28.7 |
| LMArena Vision: creative writing | 1285 Elo | Not published | Votes 2,703 · Interval (±) ±12.0 |
| LMArena Document | 1425 Elo | Not published | Votes 12,326 · Interval (±) ±7.8 |