As of October 20, 2026, Google Gemini 3.7 Flash ranks #27 of 213 models overall with 39.6 on the Artificial Analysis Intelligence Index. Its strongest category is knowledge, where it ranks #6 of 147. Google Gemini 3.7 Flash costs $0.75 per million input tokens and $3.75 per million output tokens. It was released on August 13, 2026.
Its output price ranks 240 of 349 priced models, counting from the cheapest.
Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...
google/gemini-3.7-flash 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 5 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, SWE-bench Multimodal (Vals AI), Vibe Code Bench 1-100 (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, GSO-Bench, WeirdML, MirrorCode, Cybench
Not measured on AA Agentic Index, Design Arena: HTML slides, Design Arena: PowerPoint slides, Harvey's Legal Agent Benchmark (Vals AI), BioMysteryBench (Vals AI), Vals Science Index, Time Horizon Index (Vals AI), CUA-bench (Vals AI), Robo-bench (Vals AI), τ²-Bench Telecom, METR time horizons, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, PostTrainBench, TheAgentCompany, OSWorld, SpireClimb, Vending-Bench 2, LMArena Search
Not measured on MysteryMechanism (Vals AI), Humanity's Last Exam, SimpleBench, 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), MATH level 5, GSM8K
Not measured on CaseLaw (Vals AI), CorpFin (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), Vals Multimodal Index, IFBench, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, Surface Evolver Bench, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, LMArena Vision: captioning, LMArena Vision: recognizing things, 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 | 80.5% | 20% |
| LMArena WebDevCoding | 1591 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 93.9% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 90.1% | Not in index |
| AA Intelligence IndexIntelligence | 39.6 | Not in index |
| AA Coding IndexCoding | 71.5 | Not in index |
| AA Agentic IndexAgentic work | Not measured | Not in index |
| Design Arena: websitesWeb design | 1304 | Not in index |
| Design Arena: UI componentsWeb design | 1301 | Not in index |
| Design Arena: game devWeb design | 1318 | Not in index |
| Design Arena: data vizWeb design | 1315 | Not in index |
| Design Arena: 3DWeb design | 1307 | Not in index |
| Design Arena: all code categoriesWeb design | 1309 | Not in index |
| Design Arena: SVGWeb design | 1283 | Not in index |
| Design Arena: ASCII artWeb design | 1276 | Not in index |
| Design Arena: agents building web appsAgentic work | 1221 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1209 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1227 | Not in index |
| Design Arena: agents building Android appsAgentic work | 1256 | Not in index |
| Design Arena: agents building Godot gamesAgentic work | 1264 | Not in index |
| Design Arena: agents building gamesAgentic work | 1235 | 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 | 1157 | 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 | 87.8% | Not in index |
| LiveBench data analysisGeneral | 68.0% | Not in index |
| LiveBench researchAgentic work | 76.5% | Not in index |
| LiveBench browserAgentic work | 56.0% | Not in index |
| LiveBench long agenticAgentic work | 28.3% | Not in index |
| LiveBench designWeb design | 73.2% | Not in index |
| LiveCodeBench (Vals AI)Coding | 88.7% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 80.8% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 12.1% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 70.4% | Not in index |
| Code migration (Vals AI)Coding | 34.8% | Not in index |
| ProgramBench (Vals AI)Coding | 0.0% | Not in index |
| SREBench (Vals AI)Agentic work | 4.6% | Not in index |
| IOI (Vals AI)Coding | 67.8% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 77.5% | 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 | 65.9% | Not in index |
| CyberBench (Vals AI)Coding | 43.8% | Not in index |
| Finance Agent (Vals AI)Agentic work | 59.0% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 22.8% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 34.6% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 71.3% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | Not measured | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 7.1% | 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 | 89.0% | 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 | 49.2% | Not in index |
| LegalBench (Vals AI)Knowledge | 87.3% | 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 | 74.7% | Not in index |
| MortgageTax (Vals AI)Knowledge | 66.7% | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 53.4% | Not in index |
| MedScribe (Vals AI)General | 83.9% | 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 | 94.5% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 47.9% | 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 | 59.8% | 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 | 83.0% | 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 | 65.5% | Not in index |
| FrontierCodeCoding | 43.6% | Not in index |
| FrontierSWECoding | 20.3% | 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 | 67.8% | Not in index |
| METR time horizonsAgentic work | Not measured | Not in index |
| Remote Labor IndexAgentic work | 5.0% | 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 | 94.8% | Not in index |
| ARC-AGIReasoning | 95.5% | Not in index |
| ARC-AGI-2Reasoning | 84.6% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | Not measured | Not in index |
| Chess puzzlesReasoning | 66.0% | Not in index |
| Mystery game puzzlesReasoning | 37.0% | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 97.2% | Not in index |
| FrontierMath, tiers 1 to 3Math | 71.6% | Not in index |
| FrontierMath, tier 4Math | 36.6% | Not in index |
| ProofBenchMath | 58.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 69.2% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 96.8% | Not in index |
| LMCAGeneral | 50.4% | 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 | Not measured | Not in index |
| Furniture assemblyGeneral | 26.7% | 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 | 904.3 | Not in index |
| Vending-Bench 2Agentic work | Not measured | Not in index |
| Epoch Capabilities IndexIntelligence | 157.2 | Not in index |
| LMArena TextGeneral | 1487 | Not in index |
| LMArena Text: codingCoding | 1498 | Not in index |
| LMArena Text: hard promptsReasoning | 1495 | Not in index |
| LMArena Text: mathMath | 1510 | Not in index |
| LMArena Text: instruction followingGeneral | 1484 | Not in index |
| LMArena Text: creative writingGeneral | 1489 | Not in index |
| LMArena VisionGeneral | 1314 | Not in index |
| LMArena Text: EnglishGeneral | 1483 | Not in index |
| LMArena Text: non-EnglishGeneral | 1485 | Not in index |
| LMArena Text: ChineseGeneral | 1551 | Not in index |
| LMArena Text: GermanGeneral | 1503 | Not in index |
| LMArena Text: JapaneseGeneral | 1512 | Not in index |
| LMArena Text: KoreanGeneral | 1481 | Not in index |
| LMArena Text: FrenchGeneral | 1502 | Not in index |
| LMArena Text: SpanishGeneral | 1491 | Not in index |
| LMArena Text: RussianGeneral | 1518 | Not in index |
| LMArena Text: PolishGeneral | 1502 | Not in index |
| LMArena Text: multi-turnGeneral | 1487 | Not in index |
| LMArena Text: longer queriesGeneral | 1492 | Not in index |
| LMArena Text: expertReasoning | 1510 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1487 | Not in index |
| LMArena Text: software and ITCoding | 1498 | Not in index |
| LMArena Text: mathematical workMath | 1501 | Not in index |
| LMArena Text: scienceKnowledge | 1510 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1492 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1495 | Not in index |
| LMArena Text: business and financeKnowledge | 1478 | Not in index |
| LMArena Text: writing and languageGeneral | 1491 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1479 | Not in index |
| LMArena WebDev: ReactCoding | 1587 | Not in index |
| LMArena WebDev: HTMLCoding | 1593 | Not in index |
| LMArena WebDev: from an imageCoding | 1599 | Not in index |
| LMArena Vision: EnglishGeneral | 1309 | Not in index |
| LMArena Vision: ChineseGeneral | 1394 | Not in index |
| LMArena Vision: reading textGeneral | 1322 | Not in index |
| LMArena Vision: diagramsReasoning | 1329 | Not in index |
| LMArena Vision: homeworkReasoning | 1320 | Not in index |
| LMArena Vision: humorGeneral | 1299 | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | 1312 | 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.
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 | 80.5% | $1.7317 per task | Output tokens per task 58,180 |
| LiveBench reasoning | 87.8% | $0.0689 per task | Output tokens per task 18,144 |
| LiveBench data analysis | 68.0% | $0.1667 per task | Output tokens per task 43,360 |
| LiveBench research | 76.5% | $2.6836 per task | Output tokens per task 127,694 |
| LiveBench browser | 56.0% | $1.0693 per task | Output tokens per task 27,807 |
| LiveBench long agentic | 28.3% | $5.5585 per task | Output tokens per task 205,813 |
| LiveBench design | 73.2% | $0.6231 per task | Output tokens per task 62,179 |
| SWE-bench Verified (Vals AI) | 80.8% | $1.44 per test | Duration, as printed 5m 50s |
| Terminal-Bench 4 (Vals AI) | 12.1% | $8.71 per test | Duration, as printed 1h 24m |
| Vibe Code Bench (Vals AI) | 70.4% | $4.83 per test | Duration, as printed 23m 43s |
| Code migration (Vals AI) | 34.8% | $21.46 per test | Duration, as printed 2h 39m |
| ProgramBench (Vals AI) | 0.0% | $7.13 per test | Duration, as printed 21m 30s |
| SREBench (Vals AI) | 4.6% | $21.47 per test | Duration, as printed 1h 50m |
|---|---|---|---|
| IOI (Vals AI) | 67.8% | $3.40 per test | Duration, as printed 21m 09s |
| Terminal-Bench 2.1 (Vals AI) | 77.5% | $1.02 per test | Duration, as printed 8m 12s |
| SkillsBench (Vals AI) | 65.9% | $1.80 per test | Duration, as printed 3m 06s |
| CyberBench (Vals AI) | 43.8% | $2.15 per test | Duration, as printed 7m 34s |
| Finance Agent (Vals AI) | 59.0% | $1.48 per test | Duration, as printed 3m 01s |
| Tax Agent Bench (Vals AI) | 22.8% | $0.48 per test | Duration, as printed 1m 27s |
| Legal Research Bench (Vals AI) | 34.6% | $0.76 per test | Duration, as printed 4m 49s |
| Excel Modeling Benchmark (Vals AI) | 71.3% | $5.69 per test | Duration, as printed 10m 51s |
| Terminal-Bench-Science (Vals AI) | 7.1% | $7.19 per test | Duration, as printed 1h 20m |
| DeepSWE | 65.5% | $2.0251 mean cost per task | Solved in 4 tries 83.2% · Output tokens per task 93,991 · Agent steps per task 117 |
| FrontierSWE | 20.3% | $34.14 average cost per task | Best of 5 runs 31.2% · Hours per task 7.9 h |
| ProofBench | 58.0% | $0.5585 per test | Time per proof 7m 04s |
| ALE-Bench | 904.3 | $0.2436 per problem | Tokens per problem 35,110 |
| LMArena WebDev | 1591 Elo | Not published | Votes 12,636 · Interval (±) ±6.8 |
| GPQA Diamond | 93.9% | Not published | Latency, as printed 8.8 s |
| MMLU Pro | 90.1% | Not published | Latency, as printed 4.2 s |
| Design Arena: websites | 1304 Elo | Not published | Battles 57,032 |
| Design Arena: UI components | 1301 Elo | Not published | Battles 1,904 |
| Design Arena: game dev | 1318 Elo | Not published | Battles 14,101 |
| Design Arena: data viz | 1315 Elo | Not published | Battles 1,703 |
| Design Arena: 3D | 1307 Elo | Not published | Battles 7,625 |
| Design Arena: all code categories | 1309 Elo | Not published | Battles 77,346 |
| Design Arena: SVG | 1283 Elo | Not published | Battles 3,551 |
| Design Arena: ASCII art | 1276 Elo | Not published | Battles 545 |
| Design Arena: agents building web apps | 1221 Elo | Not published | Battles 1,236 |
| Design Arena: agents building full-stack apps | 1209 Elo | Not published | Battles 682 |
| Design Arena: agents building mobile apps | 1227 Elo | Not published | Battles 650 |
| Design Arena: agents building Android apps | 1256 Elo | Not published | Battles 2,229 |
| Design Arena: agents building Godot games | 1264 Elo | Not published | Battles 461 |
| Design Arena: agents building games | 1235 Elo | Not published | Battles 4,709 |
| Design Arena: spreadsheets | 1157 Elo | Not published | Battles 22 |
| LiveCodeBench (Vals AI) | 88.7% | Not published | Latency, as printed 15 s |
| MMMU Pro (Vals AI) | 89.0% | Not published | Latency, as printed 6.3 s |
| SAGE (Vals AI) | 49.2% | Not published | Latency, as printed 9.8 s |
| LegalBench (Vals AI) | 87.3% | Not published | Latency, as printed 2.2 s |
| TaxEval (Vals AI) | 74.7% | Not published | Latency, as printed 7.8 s |
| MortgageTax (Vals AI) | 66.7% | Not published | Latency, as printed 4.1 s |
| MedCode (Vals AI) | 53.4% | Not published | Latency, as printed 9.2 s |
| MedScribe (Vals AI) | 83.9% | Not published | Latency, as printed 17 s |
| APEX-Agents | 67.8% | Not published | Mean score 79.4% |
| LMArena Text | 1487 Elo | Not published | Votes 27,232 · Interval (±) ±4.9 |
| LMArena Text: coding | 1498 Elo | Not published | Votes 7,459 · Interval (±) ±7.7 |
| LMArena Text: hard prompts | 1495 Elo | Not published | Votes 17,784 · Interval (±) ±5.7 |
| LMArena Text: math | 1510 Elo | Not published | Votes 1,390 · Interval (±) ±16.1 |
| LMArena Text: instruction following | 1484 Elo | Not published | Votes 9,766 · Interval (±) ±7.0 |
| LMArena Text: creative writing | 1489 Elo | Not published | Votes 6,003 · Interval (±) ±8.8 |
| LMArena Vision | 1314 Elo | Not published | Votes 5,369 · Interval (±) ±9.2 |
| LMArena Text: English | 1483 Elo | Not published | Votes 10,911 · Interval (±) ±6.6 |
| LMArena Text: non-English | 1485 Elo | Not published | Votes 16,312 · Interval (±) ±5.9 |
| LMArena Text: Chinese | 1551 Elo | Not published | Votes 2,124 · Interval (±) ±13.6 |
| LMArena Text: German | 1503 Elo | Not published | Votes 418 · Interval (±) ±28.8 |
| LMArena Text: Japanese | 1512 Elo | Not published | Votes 435 · Interval (±) ±30.5 |
| LMArena Text: Korean | 1481 Elo | Not published | Votes 503 · Interval (±) ±27.6 |
| LMArena Text: French | 1502 Elo | Not published | Votes 844 · Interval (±) ±21.7 |
| LMArena Text: Spanish | 1491 Elo | Not published | Votes 862 · Interval (±) ±20.9 |
| LMArena Text: Russian | 1518 Elo | Not published | Votes 3,394 · Interval (±) ±10.7 |
| LMArena Text: Polish | 1502 Elo | Not published | Votes 426 · Interval (±) ±28.5 |
| LMArena Text: multi-turn | 1487 Elo | Not published | Votes 4,139 · Interval (±) ±9.9 |
| LMArena Text: longer queries | 1492 Elo | Not published | Votes 12,678 · Interval (±) ±6.6 |
| LMArena Text: expert | 1510 Elo | Not published | Votes 3,121 · Interval (±) ±11.1 |
| LMArena Text: hard prompts in English | 1487 Elo | Not published | Votes 7,112 · Interval (±) ±7.8 |
| LMArena Text: software and IT | 1498 Elo | Not published | Votes 10,449 · Interval (±) ±6.7 |
| LMArena Text: mathematical work | 1501 Elo | Not published | Votes 1,672 · Interval (±) ±14.9 |
| LMArena Text: science | 1510 Elo | Not published | Votes 4,565 · Interval (±) ±9.3 |
| LMArena Text: medicine and healthcare | 1492 Elo | Not published | Votes 1,957 · Interval (±) ±14.0 |
| LMArena Text: legal and government | 1495 Elo | Not published | Votes 2,302 · Interval (±) ±12.9 |
| LMArena Text: business and finance | 1478 Elo | Not published | Votes 4,953 · Interval (±) ±9.0 |
| LMArena Text: writing and language | 1491 Elo | Not published | Votes 7,589 · Interval (±) ±7.9 |
| LMArena Text: entertainment and media | 1479 Elo | Not published | Votes 7,249 · Interval (±) ±8.1 |
| LMArena WebDev: React | 1587 Elo | Not published | Votes 8,109 · Interval (±) ±8.0 |
| LMArena WebDev: HTML | 1593 Elo | Not published | Votes 1,850 · Interval (±) ±15.4 |
| LMArena WebDev: from an image | 1599 Elo | Not published | Votes 2,661 · Interval (±) ±12.2 |
| LMArena Vision: English | 1309 Elo | Not published | Votes 1,848 · Interval (±) ±14.7 |
| LMArena Vision: Chinese | 1394 Elo | Not published | Votes 302 · Interval (±) ±34.1 |
| LMArena Vision: reading text | 1322 Elo | Not published | Votes 3,653 · Interval (±) ±10.3 |
| LMArena Vision: diagrams | 1329 Elo | Not published | Votes 1,364 · Interval (±) ±16.7 |
| LMArena Vision: homework | 1320 Elo | Not published | Votes 665 · Interval (±) ±22.7 |
| LMArena Vision: humor | 1299 Elo | Not published | Votes 215 · Interval (±) ±41.5 |
| LMArena Vision: creative writing | 1312 Elo | Not published | Votes 505 · Interval (±) ±27.9 |