As of October 22, 2026, OpenAI GPT-5.5 ranks #14 of 123 models overall with 69.2 ±7.7 on the LLMBenchmark Index. GPT-5.5 ranks #14 of 122 in reasoning, its strongest category. OpenAI GPT-5.5 costs $5.00 per million input tokens and $30.00 per million output tokens. GPT-5.5 was released on April 24, 2026.
GPT-5.5's output price ranks 332 of 349 priced models, counting from the cheapest.
GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
openai/gpt-5.5 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 7 of 7 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 Aider polyglot, SWE-bench Verified, SWE-bench Lite, SWE-bench (full test set), SWE-bench Multimodal, SWE-bench Multilingual, IOI (Vals AI), SWE-bench Multimodal (Vals AI), Vibe Code Bench 1-100 (Vals AI), CyberBench (Vals AI), LiveCodeBench (Artificial Analysis run), DeepSWE, FrontierSWE, Cybench, SciCode
Not measured on Design Arena: spreadsheets, Harvey's Legal Agent Benchmark (Vals AI), BioMysteryBench (Vals AI), Terminal-Bench-Science (Vals AI), Vals Science Index, CUA-bench (Vals AI), Robo-bench (Vals AI), METR time horizons, GDPval, BALROG, TheAgentCompany, OSWorld, SpireClimb, LMArena Search, Berkeley Function Calling Leaderboard (BFCL), BrowseComp-Plus
Not measured on MysteryMechanism (Vals AI), Humanity's Last Exam, 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 MedQA (Vals AI), MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on Vals Index, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, HellaSwag, WinoGrande, PIQA, LMArena Vision: captioning
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 | Not in index |
| SWE-bench VerifiedCoding | Not measured | Not in index |
| 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 | 85.1% | 15% |
| LMArena WebDevCoding | 1513 | 10% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 93.2% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 88.1% | Not in index |
| AA Intelligence IndexIntelligence | 38.4 | Not in index |
| AA Coding IndexCoding | 74.9 | Not in index |
| AA Agentic IndexAgentic work | 36.4 | Not in index |
| Design Arena: websitesWeb design | 1256 | Not in index |
| Design Arena: UI componentsWeb design | 1257 | Not in index |
| Design Arena: game devWeb design | 1293 | Not in index |
| Design Arena: data vizWeb design | 1264 | Not in index |
| Design Arena: 3DWeb design | 1197 | Not in index |
| Design Arena: all code categoriesWeb design | 1260 | Not in index |
| Design Arena: SVGWeb design | 1234 | Not in index |
| Design Arena: ASCII artWeb design | 1255 | Not in index |
| Design Arena: agents building web appsAgentic work | 1117 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1089 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1142 | Not in index |
| Design Arena: agents building Android appsAgentic work | 1164 | Not in index |
| Design Arena: agents building Godot gamesAgentic work | 1173 | Not in index |
| Design Arena: agents building gamesAgentic work | 1179 | Not in index |
| Design Arena: HTML slidesAgentic work | 1017 | Not in index |
| Design Arena: PowerPoint slidesAgentic work | 1084 | 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 | 89.7% | Not in index |
| LiveBench data analysisGeneral | 81.6% | Not in index |
| LiveBench researchAgentic work | 61.6% | Not in index |
| LiveBench browserAgentic work | 48.0% | Not in index |
| LiveBench long agenticAgentic work | 44.6% | Not in index |
| LiveBench designWeb design | 70.3% | Not in index |
| LiveCodeBench (Vals AI)Coding | 85.3% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 82.6% | 15% |
| Terminal-Bench 4 (Vals AI)Coding | Not measured | 25% |
| Vibe Code Bench (Vals AI)Coding | 69.8% | 20% |
| Code migration (Vals AI)Coding | 45.2% | Not in index |
| ProgramBench (Vals AI)Coding | 0.5% | Not in index |
| SREBench (Vals AI)Agentic work | 3.8% | Not in index |
| IOI (Vals AI)Coding | Not measured | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 76.4% | 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 | 62.5% | Not in index |
| CyberBench (Vals AI)Coding | Not measured | Not in index |
| Finance Agent (Vals AI)Agentic work | 51.8% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 21.8% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 40.4% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 64.5% | 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 | 8.3% | 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 | 60.9% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | Not measured | Not in index |
| MMMU Pro (Vals AI)Reasoning | 88.3% | 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 | 51.5% | Not in index |
| LegalBench (Vals AI)Knowledge | 86.5% | Not in index |
| CaseLaw (Vals AI)Knowledge | 66.2% | Not in index |
| CorpFin (Vals AI)Knowledge | 68.4% | Not in index |
| TaxEval (Vals AI)Knowledge | 75.0% | Not in index |
| MortgageTax (Vals AI)Knowledge | 68.8% | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 49.1% | Not in index |
| MedScribe (Vals AI)General | 86.9% | Not in index |
| Vals Multimodal IndexGeneral | 68.1% | Not in index |
| AA Math IndexMath | Not measured | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | 93.5% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 45.8% | 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 | 56.1% | Not in index |
| Terminal-Bench Hard (Artificial Analysis run)Coding | 60.6% | Not in index |
| IFBenchGeneral | 75.9% | Not in index |
| Long context reasoning (AA-LCR)General | 84.3% | Not in index |
| τ²-Bench TelecomAgentic work | 93.9% | Not in index |
| AIME 2025 (Artificial Analysis run)Math | Not measured | Not in index |
| Terminal-BenchCoding | 84.7% | Not in index |
| DeepSWECoding | Not measured | Not in index |
| FrontierCodeCoding | 43.0% | 15% |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | 40.2% | Not in index |
| WeirdMLCoding | 84.9% | Not in index |
| MirrorCodeCoding | 10.0% | Not in index |
| APEX-AgentsAgentic work | 55.1% | Not in index |
| METR time horizonsAgentic work | Not measured | Not in index |
| Remote Labor IndexAgentic work | 6.3% | Not in index |
| GDPvalAgentic work | Not measured | Not in index |
| OSWorld 2.0Agentic work | 13.0% | Not in index |
| BALROGAgentic work | Not measured | Not in index |
| DeepResearch BenchAgentic work | 54.0% | Not in index |
| PostTrainBenchAgentic work | 27.2% | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 90.7% | Not in index |
| ARC-AGIReasoning | 95.0% | Not in index |
| ARC-AGI-2Reasoning | 85.0% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | 69.0% | Not in index |
| Chess puzzlesReasoning | 63.0% | Not in index |
| Mystery game puzzlesReasoning | 56.0% | Not in index |
| EBR-benchReasoning | 34.3% | Not in index |
| OTIS Mock AIMEMath | 84.4% | Not in index |
| FrontierMath, tiers 1 to 3Math | 85.3% | Not in index |
| FrontierMath, tier 4Math | 72.5% | Not in index |
| ProofBenchMath | 50.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 63.0% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 96.0% | Not in index |
| LMCAGeneral | 54.3% | 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 | 88.1% | Not in index |
| Furniture assemblyGeneral | 44.2% | Not in index |
| ExploitBenchGeneral | 47.4% | 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 | 22.2% | Not in index |
| ALE-BenchCoding | 1943.0 | Not in index |
| Vending-Bench 2Agentic work | $7,524 | Not in index |
| Epoch Capabilities IndexIntelligence | 159.7 | Not in index |
| LMArena TextGeneral | 1471 | Not in index |
| LMArena Text: codingCoding | 1494 | Not in index |
| LMArena Text: hard promptsReasoning | 1489 | Not in index |
| LMArena Text: mathMath | 1487 | Not in index |
| LMArena Text: instruction followingGeneral | 1478 | Not in index |
| LMArena Text: creative writingGeneral | 1455 | Not in index |
| LMArena VisionGeneral | 1297 | Not in index |
| LMArena Text: EnglishGeneral | 1470 | Not in index |
| LMArena Text: non-EnglishGeneral | 1467 | Not in index |
| LMArena Text: ChineseGeneral | 1534 | Not in index |
| LMArena Text: GermanGeneral | 1480 | Not in index |
| LMArena Text: JapaneseGeneral | 1499 | Not in index |
| LMArena Text: KoreanGeneral | 1460 | Not in index |
| LMArena Text: FrenchGeneral | 1485 | Not in index |
| LMArena Text: SpanishGeneral | 1468 | Not in index |
| LMArena Text: RussianGeneral | 1473 | Not in index |
| LMArena Text: PolishGeneral | 1465 | Not in index |
| LMArena Text: multi-turnGeneral | 1476 | Not in index |
| LMArena Text: longer queriesGeneral | 1484 | Not in index |
| LMArena Text: expertReasoning | 1507 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1483 | Not in index |
| LMArena Text: software and ITCoding | 1493 | Not in index |
| LMArena Text: mathematical workMath | 1496 | Not in index |
| LMArena Text: scienceKnowledge | 1485 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1465 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1491 | Not in index |
| LMArena Text: business and financeKnowledge | 1478 | Not in index |
| LMArena Text: writing and languageGeneral | 1466 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1449 | Not in index |
| LMArena WebDev: ReactCoding | 1506 | Not in index |
| LMArena WebDev: HTMLCoding | 1543 | Not in index |
| LMArena WebDev: from an imageCoding | 1532 | Not in index |
| LMArena Vision: EnglishGeneral | 1292 | Not in index |
| LMArena Vision: ChineseGeneral | 1360 | Not in index |
| LMArena Vision: reading textGeneral | 1306 | Not in index |
| LMArena Vision: diagramsReasoning | 1325 | Not in index |
| LMArena Vision: homeworkReasoning | 1332 | Not in index |
| LMArena Vision: humorGeneral | 1293 | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | 1231 | Not in index |
| LMArena Vision: creative writingGeneral | 1301 | Not in index |
| LMArena SearchAgentic work | Not measured | Not in index |
| LMArena DocumentGeneral | 1486 | Not in index |
| LMArena Text to ImageImage generation | Not measured | Not in index |
| LMArena Image EditImage generation | Not measured | Not in index |
| Berkeley Function Calling Leaderboard (BFCL)Agentic work | Not measured | Not in index |
| Kagi LLM BenchmarkReasoning | 88.8% | Not in index |
| BrowseComp-PlusAgentic work | Not measured | Not in index |
| SciCodeCoding | Not measured | Not in index |
| FACTS Benchmark SuiteKnowledge | 66.7% | 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 | 85.1% | $4.2076 per task | Output tokens per task 18,415 |
| LiveBench reasoning | 89.7% | $0.2892 per task | Output tokens per task 9,457 |
| LiveBench data analysis | 81.6% | $0.4055 per task | Output tokens per task 13,299 |
| LiveBench research | 61.6% | $17.1379 per task | Output tokens per task 21,217 |
| LiveBench browser | 48.0% | $5.62 per task | Output tokens per task 79,713 |
| LiveBench long agentic | 44.6% | $13.8515 per task | Output tokens per task 95,488 |
| LiveBench design | 70.3% | $1.1904 per task | Output tokens per task 17,832 |
| SWE-bench Verified (Vals AI) | 82.6% | $1.36 per test | Duration, as printed 7m 06s |
| Vibe Code Bench (Vals AI) | 69.8% | $16.66 per test | Duration, as printed 31m 52s |
| Code migration (Vals AI) | 45.2% | $6.44 per test | Duration, as printed 31m 35s |
| ProgramBench (Vals AI) | 0.5% | $6.95 per test | Duration, as printed 22m 03s |
| SREBench (Vals AI) | 3.8% | $17.77 per test | Duration, as printed 46m 28s |
| Terminal-Bench 2.1 (Vals AI) | 76.4% | $0.74 per test | Duration, as printed 7m 07s |
|---|---|---|---|
| SkillsBench (Vals AI) | 62.5% | $1.57 per test | Duration, as printed 4m 40s |
| Finance Agent (Vals AI) | 51.8% | $4.15 per test | Duration, as printed 11m 02s |
| Tax Agent Bench (Vals AI) | 21.8% | $4.07 per test | Duration, as printed 15m 52s |
| Legal Research Bench (Vals AI) | 40.4% | $7.40 per test | Duration, as printed 37m 45s |
| Excel Modeling Benchmark (Vals AI) | 64.5% | $3.27 per test | Duration, as printed 15m 11s |
| Public Benefits Bench (Vals AI) | 60.9% | $3.97 per test | Nothing else |
| Vals Multimodal Index | 68.1% | $3.32 per test | Duration, as printed 8m 24s |
| WeirdML | 84.9% | $2.5683 per run | Median lines of code 517 |
| OSWorld 2.0 | 13.0% | $2750.00 estimated cost | With partial credit 49.5% |
| ARC-AGI | 95.0% | $0.73 per task | Nothing else |
| ARC-AGI-2 | 85.0% | $1.87 per task | Nothing else |
| ProofBench | 50.0% | $1.6818 per test | Time per proof 49m 13s |
| Surface Evolver Bench | 88.1% | $13.8258 of the run | Pass rate 75.0% · Tokens for the run 2.0M |
| ALE-Bench | 1943.0 | $1.5171 per problem | Tokens per problem 54,091 |
| Kagi LLM Benchmark | 88.8% | $2.20 of the suite | Nothing else |
| LMArena WebDev | 1513 Elo | Not published | Votes 15,612 · Interval (±) ±6.0 |
| GPQA Diamond | 93.2% | Not published | Latency, as printed 1m 52s |
| MMLU Pro | 88.1% | Not published | Latency, as printed 42 s |
| Design Arena: websites | 1256 Elo | Not published | Battles 19,012 |
| Design Arena: UI components | 1257 Elo | Not published | Battles 2,533 |
| Design Arena: game dev | 1293 Elo | Not published | Battles 7,279 |
| Design Arena: data viz | 1264 Elo | Not published | Battles 1,644 |
| Design Arena: 3D | 1197 Elo | Not published | Battles 5,749 |
| Design Arena: all code categories | 1260 Elo | Not published | Battles 33,995 |
| Design Arena: SVG | 1234 Elo | Not published | Battles 3,272 |
| Design Arena: ASCII art | 1255 Elo | Not published | Battles 557 |
| Design Arena: agents building web apps | 1117 Elo | Not published | Battles 5,342 |
| Design Arena: agents building full-stack apps | 1089 Elo | Not published | Battles 3,539 |
| Design Arena: agents building mobile apps | 1142 Elo | Not published | Battles 843 |
| Design Arena: agents building Android apps | 1164 Elo | Not published | Battles 1,611 |
| Design Arena: agents building Godot games | 1173 Elo | Not published | Battles 1,226 |
| Design Arena: agents building games | 1179 Elo | Not published | Battles 2,275 |
| Design Arena: HTML slides | 1017 Elo | Not published | Battles 2,055 |
| Design Arena: PowerPoint slides | 1084 Elo | Not published | Battles 1,237 |
| LiveCodeBench (Vals AI) | 85.3% | Not published | Latency, as printed 2m 47s |
| MMMU Pro (Vals AI) | 88.3% | Not published | Latency, as printed 54 s |
| SAGE (Vals AI) | 51.5% | Not published | Latency, as printed 1m 16s |
| LegalBench (Vals AI) | 86.5% | Not published | Latency, as printed 18 s |
| CaseLaw (Vals AI) | 66.2% | Not published | Latency, as printed 25 s |
| CorpFin (Vals AI) | 68.4% | Not published | Latency, as printed 23 s |
| TaxEval (Vals AI) | 75.0% | Not published | Latency, as printed 1m 36s |
| MortgageTax (Vals AI) | 68.8% | Not published | Latency, as printed 28 s |
| MedCode (Vals AI) | 49.1% | Not published | Latency, as printed 2m 40s |
| MedScribe (Vals AI) | 86.9% | Not published | Latency, as printed 2m 13s |
| APEX-Agents | 55.1% | Not published | Mean score 70.3% |
| LMArena Text | 1471 Elo | Not published | Votes 69,340 · Interval (±) ±3.7 |
| LMArena Text: coding | 1494 Elo | Not published | Votes 19,152 · Interval (±) ±5.7 |
| LMArena Text: hard prompts | 1489 Elo | Not published | Votes 45,527 · Interval (±) ±4.3 |
| LMArena Text: math | 1487 Elo | Not published | Votes 3,518 · Interval (±) ±10.4 |
| LMArena Text: instruction following | 1478 Elo | Not published | Votes 24,002 · Interval (±) ±5.3 |
| LMArena Text: creative writing | 1455 Elo | Not published | Votes 13,147 · Interval (±) ±6.5 |
| LMArena Vision | 1297 Elo | Not published | Votes 28,781 · Interval (±) ±5.8 |
| LMArena Text: English | 1470 Elo | Not published | Votes 31,535 · Interval (±) ±4.8 |
| LMArena Text: non-English | 1467 Elo | Not published | Votes 37,804 · Interval (±) ±4.5 |
| LMArena Text: Chinese | 1534 Elo | Not published | Votes 4,471 · Interval (±) ±9.7 |
| LMArena Text: German | 1480 Elo | Not published | Votes 1,113 · Interval (±) ±19.0 |
| LMArena Text: Japanese | 1499 Elo | Not published | Votes 907 · Interval (±) ±21.3 |
| LMArena Text: Korean | 1460 Elo | Not published | Votes 1,180 · Interval (±) ±18.3 |
| LMArena Text: French | 1485 Elo | Not published | Votes 2,511 · Interval (±) ±13.7 |
| LMArena Text: Spanish | 1468 Elo | Not published | Votes 1,945 · Interval (±) ±14.3 |
| LMArena Text: Russian | 1473 Elo | Not published | Votes 7,412 · Interval (±) ±7.6 |
| LMArena Text: Polish | 1465 Elo | Not published | Votes 1,168 · Interval (±) ±17.5 |
| LMArena Text: multi-turn | 1476 Elo | Not published | Votes 11,821 · Interval (±) ±6.7 |
| LMArena Text: longer queries | 1484 Elo | Not published | Votes 32,009 · Interval (±) ±5.0 |
| LMArena Text: expert | 1507 Elo | Not published | Votes 7,400 · Interval (±) ±7.7 |
| LMArena Text: hard prompts in English | 1483 Elo | Not published | Votes 21,950 · Interval (±) ±5.4 |
| LMArena Text: software and IT | 1493 Elo | Not published | Votes 27,452 · Interval (±) ±5.0 |
| LMArena Text: mathematical work | 1496 Elo | Not published | Votes 3,975 · Interval (±) ±10.1 |
| LMArena Text: science | 1485 Elo | Not published | Votes 11,611 · Interval (±) ±6.5 |
| LMArena Text: medicine and healthcare | 1465 Elo | Not published | Votes 5,318 · Interval (±) ±9.0 |
| LMArena Text: legal and government | 1491 Elo | Not published | Votes 5,610 · Interval (±) ±8.7 |
| LMArena Text: business and finance | 1478 Elo | Not published | Votes 13,713 · Interval (±) ±6.3 |
| LMArena Text: writing and language | 1466 Elo | Not published | Votes 18,160 · Interval (±) ±5.8 |
| LMArena Text: entertainment and media | 1449 Elo | Not published | Votes 16,698 · Interval (±) ±6.0 |
| LMArena WebDev: React | 1506 Elo | Not published | Votes 12,062 · Interval (±) ±6.6 |
| LMArena WebDev: HTML | 1543 Elo | Not published | Votes 1,870 · Interval (±) ±15.0 |
| LMArena WebDev: from an image | 1532 Elo | Not published | Votes 6,795 · Interval (±) ±9.2 |
| LMArena Vision: English | 1292 Elo | Not published | Votes 11,422 · Interval (±) ±8.0 |
| LMArena Vision: Chinese | 1360 Elo | Not published | Votes 1,777 · Interval (±) ±16.6 |
| LMArena Vision: reading text | 1306 Elo | Not published | Votes 20,286 · Interval (±) ±5.8 |
| LMArena Vision: diagrams | 1325 Elo | Not published | Votes 7,798 · Interval (±) ±8.1 |
| LMArena Vision: homework | 1332 Elo | Not published | Votes 3,535 · Interval (±) ±10.8 |
| LMArena Vision: humor | 1293 Elo | Not published | Votes 1,075 · Interval (±) ±18.5 |
| LMArena Vision: recognizing things | 1231 Elo | Not published | Votes 119 · Interval (±) ±52.3 |
| LMArena Vision: creative writing | 1301 Elo | Not published | Votes 2,038 · Interval (±) ±13.9 |
| LMArena Document | 1486 Elo | Not published | Votes 21,279 · Interval (±) ±6.2 |