As of October 20, 2026, Anthropic Claude Opus 5.5 ranks #1 of 213 models overall with 57.6 on the Artificial Analysis Intelligence Index. Its strongest category is coding, where it ranks #1 of 136. Anthropic Claude Opus 5.5 costs $4.00 per million input tokens and $20.00 per million output tokens. It was released on September 22, 2026.
Its output price ranks 323 of 349 priced models, counting from the cheapest.
Listed on OpenRouter September 22, 2026, 28 days before our data. Results so far on 105 of 190 public boards; this page updates every day as boards publish.
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...
anthropic/claude-opus-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 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), SkillsBench (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, DeepSWE, GSO-Bench, WeirdML, Cybench
Not measured on AA Agentic Index, Design Arena: agents building full-stack 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, τ²-Bench Telecom, METR time horizons, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, PostTrainBench, TheAgentCompany, OSWorld
Not measured on GPQA Diamond, MMMU Pro (Vals AI), GPQA Diamond (Artificial Analysis run), Humanity's Last Exam, SimpleBench, 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 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 Design Arena: ASCII art
Not measured on Vals Multimodal Index, IFBench, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, Surface Evolver 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 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 | 96.3% | 20% |
| LMArena WebDevCoding | 1807 | 15% |
| Vals IndexGeneral | 70.2% | 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 | 57.6 | Not in index |
| AA Coding IndexCoding | Not measured | Not in index |
| AA Agentic IndexAgentic work | Not measured | Not in index |
| Design Arena: websitesWeb design | 1336 | Not in index |
| Design Arena: UI componentsWeb design | 1386 | Not in index |
| Design Arena: game devWeb design | 1458 | Not in index |
| Design Arena: data vizWeb design | 1397 | Not in index |
| Design Arena: 3DWeb design | 1477 | Not in index |
| Design Arena: all code categoriesWeb design | 1390 | Not in index |
| Design Arena: SVGWeb design | 1332 | Not in index |
| Design Arena: ASCII artWeb design | Not measured | Not in index |
| Design Arena: agents building web appsAgentic work | 1318 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | Not measured | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1323 | 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 | 92.2% | Not in index |
| LiveBench data analysisGeneral | 80.3% | Not in index |
| LiveBench researchAgentic work | 85.0% | Not in index |
| LiveBench browserAgentic work | 80.0% | Not in index |
| LiveBench long agenticAgentic work | 85.0% | Not in index |
| LiveBench designWeb design | 86.9% | 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 | 65.2% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 90.3% | Not in index |
| Code migration (Vals AI)Coding | 66.7% | Not in index |
| ProgramBench (Vals AI)Coding | 18.5% | Not in index |
| SREBench (Vals AI)Agentic work | 33.6% | Not in index |
| IOI (Vals AI)Coding | 95.1% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 87.6% | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | 70.2% | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | 30.4% | Not in index |
| SkillsBench (Vals AI)Coding | Not measured | Not in index |
| CyberBench (Vals AI)Coding | 74.6% | Not in index |
| Finance Agent (Vals AI)Agentic work | 58.6% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 45.6% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 50.5% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | 9.2% | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 75.9% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | 79.3% | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 47.1% | Not in index |
| Vals Science IndexAgentic work | 58.7% | Not in index |
| Time Horizon Index (Vals AI)Agentic work | 91.3% | Not in index |
| CUA-bench (Vals AI)Agentic work | 14.0% | Not in index |
| Robo-bench (Vals AI)Agentic work | 14.6% | Not in index |
| Public Benefits Bench (Vals AI)General | 70.6% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | 49.5% | 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 | 45.8% | 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 | 49.8% | Not in index |
| MedScribe (Vals AI)General | 91.4% | 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 | 61.4% | 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 | 66.9% | 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 | 84.7% | 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 | 54.6% | Not in index |
| FrontierSWECoding | 62.3% | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | Not measured | Not in index |
| MirrorCodeCoding | 77.4% | Not in index |
| APEX-AgentsAgentic work | 73.5% | Not in index |
| METR time horizonsAgentic work | Not measured | Not in index |
| Remote Labor IndexAgentic work | 21.3% | 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 | 90.6% | Not in index |
| ARC-AGIReasoning | 98.5% | Not in index |
| ARC-AGI-2Reasoning | 93.3% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | Not measured | Not in index |
| Chess puzzlesReasoning | 67.0% | Not in index |
| Mystery game puzzlesReasoning | 71.0% | Not in index |
| EBR-benchReasoning | 71.4% | Not in index |
| OTIS Mock AIMEMath | 100.0% | Not in index |
| FrontierMath, tiers 1 to 3Math | 91.2% | Not in index |
| FrontierMath, tier 4Math | 95.0% | Not in index |
| ProofBenchMath | 100.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 72.2% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 98.9% | Not in index |
| LMCAGeneral | 68.2% | 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 | 83.3% | 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 | 3.3% | 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 | 2147.4 | Not in index |
| Vending-Bench 2Agentic work | $9,235 | Not in index |
| Epoch Capabilities IndexIntelligence | 166.8 | Not in index |
| LMArena TextGeneral | 1516 | Not in index |
| LMArena Text: codingCoding | 1545 | Not in index |
| LMArena Text: hard promptsReasoning | 1535 | Not in index |
| LMArena Text: mathMath | 1508 | Not in index |
| LMArena Text: instruction followingGeneral | 1536 | Not in index |
| LMArena Text: creative writingGeneral | 1534 | Not in index |
| LMArena VisionGeneral | 1321 | Not in index |
| LMArena Text: EnglishGeneral | 1517 | Not in index |
| LMArena Text: non-EnglishGeneral | 1507 | Not in index |
| LMArena Text: ChineseGeneral | 1584 | 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 | 1505 | Not in index |
| LMArena Text: SpanishGeneral | 1519 | Not in index |
| LMArena Text: RussianGeneral | 1519 | Not in index |
| LMArena Text: PolishGeneral | Not measured | Not in index |
| LMArena Text: multi-turnGeneral | 1502 | Not in index |
| LMArena Text: longer queriesGeneral | 1531 | Not in index |
| LMArena Text: expertReasoning | 1550 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1533 | Not in index |
| LMArena Text: software and ITCoding | 1538 | Not in index |
| LMArena Text: mathematical workMath | 1506 | Not in index |
| LMArena Text: scienceKnowledge | 1522 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1513 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1510 | Not in index |
| LMArena Text: business and financeKnowledge | 1492 | Not in index |
| LMArena Text: writing and languageGeneral | 1534 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1511 | Not in index |
| LMArena WebDev: ReactCoding | 1855 | Not in index |
| LMArena WebDev: HTMLCoding | 1753 | Not in index |
| LMArena WebDev: from an imageCoding | 1753 | Not in index |
| LMArena Vision: EnglishGeneral | 1317 | Not in index |
| LMArena Vision: ChineseGeneral | Not measured | Not in index |
| LMArena Vision: reading textGeneral | 1326 | Not in index |
| LMArena Vision: diagramsReasoning | 1345 | Not in index |
| LMArena Vision: homeworkReasoning | 1362 | 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 | 1320 | Not in index |
| LMArena SearchAgentic work | 1213 | 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: $5.031, at a score of 96.3%. LiveBench counts that as $5.224 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 | 96.3% | $5.0308 per task | Output tokens per task 84,646 |
| Vals Index | 70.2% | $28.12 per test | Duration, as printed 1h 25m |
| LiveBench reasoning | 92.2% | $0.2522 per task | Output tokens per task 12,280 |
| LiveBench data analysis | 80.3% | $0.8146 per task | Output tokens per task 39,924 |
| LiveBench research | 85.0% | $8.8178 per task | Output tokens per task 129,426 |
| LiveBench browser | 80.0% | $14.6698 per task | Output tokens per task 34,270 |
| LiveBench long agentic | 85.0% | $38.0088 per task | Output tokens per task 463,030 |
| LiveBench design | 86.9% | $5.7483 per task | Output tokens per task 150,005 |
| Terminal-Bench 4 (Vals AI) | 65.2% | $13.20 per test | Duration, as printed 1h 04m |
| Vibe Code Bench (Vals AI) | 90.3% | $57.92 per test | Duration, as printed 1h 36m |
| Code migration (Vals AI) | 66.7% | $112.97 per test | Duration, as printed 3h 19m |
| ProgramBench (Vals AI) | 18.5% | $68.05 per test | Duration, as printed 2h 24m |
| SREBench (Vals AI) | 33.6% | $34.65 per test | Duration, as printed 1h 37m |
|---|---|---|---|
| IOI (Vals AI) | 95.1% | $5.26 per test | Duration, as printed 17m 15s |
| Terminal-Bench 2.1 (Vals AI) | 87.6% | $0.50 per test | Duration, as printed 6m 23s |
| SWE-bench Multimodal (Vals AI) | 70.2% | $4.92 per test | Duration, as printed 18m 32s |
| Vibe Code Bench 1-100 (Vals AI) | 30.4% | $44.12 per test | Duration, as printed 2h 28m |
| CyberBench (Vals AI) | 74.6% | $4.17 per test | Duration, as printed 23m 02s |
| Finance Agent (Vals AI) | 58.6% | $9.22 per test | Duration, as printed 33m 08s |
| Tax Agent Bench (Vals AI) | 45.6% | $15.09 per test | Duration, as printed 1h 07m |
| Legal Research Bench (Vals AI) | 50.5% | $25.16 per test | Duration, as printed 1h 52m |
| Harvey's Legal Agent Benchmark (Vals AI) | 9.2% | $21.38 per test | Duration, as printed 58m 27s |
| Excel Modeling Benchmark (Vals AI) | 75.9% | $11.02 per test | Duration, as printed 35m 06s |
| BioMysteryBench (Vals AI) | 79.3% | $3.64 per test | Duration, as printed 12m 19s |
| Terminal-Bench-Science (Vals AI) | 47.1% | $19.12 per test | Duration, as printed 2h 28m |
| Vals Science Index | 58.7% | $9.13 per test | Duration, as printed 1h 00m |
| Public Benefits Bench (Vals AI) | 70.6% | $5.95 per test | Nothing else |
| MysteryMechanism (Vals AI) | 49.5% | $4.62 per test | Duration, as printed 19m 38s |
| FrontierSWE | 62.3% | $98.87 average cost per task | Best of 5 runs 71.5% · Hours per task 14.3 h |
| ProofBench | 100.0% | $0.9616 per test | Time per proof 5m 51s |
| ALE-Bench | 2147.4 | $0.2712 per problem | Tokens per problem 16,891 |
| LMArena WebDev | 1807 Elo | Not published | Votes 2,925 · Interval (±) ±13.8 |
| Design Arena: websites | 1336 Elo | Not published | Battles 2,127 |
| Design Arena: UI components | 1386 Elo | Not published | Battles 371 |
| Design Arena: game dev | 1458 Elo | Not published | Battles 765 |
| Design Arena: data viz | 1397 Elo | Not published | Battles 638 |
| Design Arena: 3D | 1477 Elo | Not published | Battles 857 |
| Design Arena: all code categories | 1390 Elo | Not published | Battles 4,531 |
| Design Arena: SVG | 1332 Elo | Not published | Battles 998 |
| Design Arena: agents building web apps | 1318 Elo | Not published | Battles 507 |
| Design Arena: agents building mobile apps | 1323 Elo | Not published | Battles 610 |
| SAGE (Vals AI) | 45.8% | Not published | Latency, as printed 1m 54s |
| MedCode (Vals AI) | 49.8% | Not published | Latency, as printed 4m 07s |
| MedScribe (Vals AI) | 91.4% | Not published | Latency, as printed 7m 22s |
| APEX-Agents | 73.5% | Not published | Mean score 81.3% |
| LMArena Text | 1516 Elo | Not published | Votes 8,300 · Interval (±) ±7.3 |
| LMArena Text: coding | 1545 Elo | Not published | Votes 1,894 · Interval (±) ±13.8 |
| LMArena Text: hard prompts | 1535 Elo | Not published | Votes 5,157 · Interval (±) ±9.0 |
| LMArena Text: math | 1508 Elo | Not published | Votes 416 · Interval (±) ±28.3 |
| LMArena Text: instruction following | 1536 Elo | Not published | Votes 2,851 · Interval (±) ±11.8 |
| LMArena Text: creative writing | 1534 Elo | Not published | Votes 1,945 · Interval (±) ±15.0 |
| LMArena Vision | 1321 Elo | Not published | Votes 3,035 · Interval (±) ±11.7 |
| LMArena Text: English | 1517 Elo | Not published | Votes 3,165 · Interval (±) ±11.1 |
| LMArena Text: non-English | 1507 Elo | Not published | Votes 5,130 · Interval (±) ±9.0 |
| LMArena Text: Chinese | 1584 Elo | Not published | Votes 767 · Interval (±) ±22.0 |
| LMArena Text: French | 1505 Elo | Not published | Votes 284 · Interval (±) ±35.2 |
| LMArena Text: Spanish | 1519 Elo | Not published | Votes 294 · Interval (±) ±33.5 |
| LMArena Text: Russian | 1519 Elo | Not published | Votes 1,089 · Interval (±) ±18.2 |
| LMArena Text: multi-turn | 1502 Elo | Not published | Votes 1,088 · Interval (±) ±18.4 |
| LMArena Text: longer queries | 1531 Elo | Not published | Votes 3,519 · Interval (±) ±11.0 |
| LMArena Text: expert | 1550 Elo | Not published | Votes 907 · Interval (±) ±19.9 |
| LMArena Text: hard prompts in English | 1533 Elo | Not published | Votes 1,990 · Interval (±) ±13.8 |
| LMArena Text: software and IT | 1538 Elo | Not published | Votes 2,904 · Interval (±) ±11.3 |
| LMArena Text: mathematical work | 1506 Elo | Not published | Votes 467 · Interval (±) ±26.2 |
| LMArena Text: science | 1522 Elo | Not published | Votes 1,439 · Interval (±) ±16.1 |
| LMArena Text: medicine and healthcare | 1513 Elo | Not published | Votes 564 · Interval (±) ±26.0 |
| LMArena Text: legal and government | 1510 Elo | Not published | Votes 712 · Interval (±) ±23.0 |
| LMArena Text: business and finance | 1492 Elo | Not published | Votes 1,479 · Interval (±) ±15.8 |
| LMArena Text: writing and language | 1534 Elo | Not published | Votes 2,477 · Interval (±) ±13.1 |
| LMArena Text: entertainment and media | 1511 Elo | Not published | Votes 2,212 · Interval (±) ±13.8 |
| LMArena WebDev: React | 1855 Elo | Not published | Votes 2,007 · Interval (±) ±17.3 |
| LMArena WebDev: HTML | 1753 Elo | Not published | Votes 135 · Interval (±) ±60.8 |
| LMArena WebDev: from an image | 1753 Elo | Not published | Votes 781 · Interval (±) ±24.0 |
| LMArena Vision: English | 1317 Elo | Not published | Votes 992 · Interval (±) ±19.9 |
| LMArena Vision: reading text | 1326 Elo | Not published | Votes 2,118 · Interval (±) ±13.5 |
| LMArena Vision: diagrams | 1345 Elo | Not published | Votes 711 · Interval (±) ±22.9 |
| LMArena Vision: homework | 1362 Elo | Not published | Votes 422 · Interval (±) ±29.4 |
| LMArena Vision: creative writing | 1320 Elo | Not published | Votes 283 · Interval (±) ±37.4 |
| LMArena Search | 1213 Elo | Not published | Votes 10,842 · Interval (±) ±7.1 |