As of October 20, 2026, OpenAI gpt-oss-120b ranks #144 of 213 models overall with 11.6 on the Artificial Analysis Intelligence Index. Its strongest category is math, where it ranks #50 of 116. OpenAI gpt-oss-120b costs $0.15 per million input tokens and $0.60 per million output tokens. It was released on August 5, 2025.
Its output price ranks 96 of 349 priced models, counting from the cheapest.
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
openai/gpt-oss-120b 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 6 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, 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), DeepSWE, FrontierCode, FrontierSWE, GSO-Bench, MirrorCode, Cybench, LMArena WebDev: React, LMArena WebDev: HTML, 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, LiveBench research, LiveBench browser, LiveBench long agentic, 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), Remote Labor Index, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, PostTrainBench, TheAgentCompany, OSWorld, SpireClimb, LMArena Search
Not measured on LiveBench reasoning, MysteryMechanism (Vals AI), MMMU Pro (Vals AI), ARC-AGI, ARC-AGI-2, Humanity's Last Exam, Chess puzzles, EBR-bench, VPCT, BIG-Bench Hard, LMArena Vision: diagrams, LMArena Vision: homework
Not measured on FrontierMath, tiers 1 to 3, FrontierMath, tier 4, ProofBench, MATH level 5, GSM8K
Not measured on MortgageTax (Vals AI), MedCode (Vals AI), SimpleQA Verified, MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on Design Arena: SVG, Design Arena: ASCII art, LiveBench design
Not measured on Vals Index, LiveBench data analysis, Public Benefits Bench (Vals AI), SAGE (Vals AI), MedScribe (Vals AI), Vals Multimodal Index, CL-bench, Furniture assembly, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, LMArena Vision, LMArena Vision: English, LMArena Vision: Chinese, LMArena Vision: reading text, 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 | 41.8% | 35% |
| SWE-bench VerifiedCoding | 26.0% | 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 | Not measured | 20% |
| LMArena WebDevCoding | Not measured | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 78.5% | Not in index |
| AIMEMath | 92.6% | Not in index |
| MMLU ProKnowledge | 79.2% | Not in index |
| AA Intelligence IndexIntelligence | 11.6 | Not in index |
| AA Coding IndexCoding | 30.4 | Not in index |
| AA Agentic IndexAgentic work | 3.7 | Not in index |
| Design Arena: websitesWeb design | 968 | Not in index |
| Design Arena: UI componentsWeb design | 927 | Not in index |
| Design Arena: game devWeb design | 992 | Not in index |
| Design Arena: data vizWeb design | 987 | Not in index |
| Design Arena: 3DWeb design | 901 | Not in index |
| Design Arena: all code categoriesWeb design | 963 | 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 | Not measured | Not in index |
| LiveBench data analysisGeneral | Not measured | Not in index |
| LiveBench researchAgentic work | Not measured | Not in index |
| LiveBench browserAgentic work | Not measured | Not in index |
| LiveBench long agenticAgentic work | Not measured | Not in index |
| LiveBench designWeb design | Not measured | Not in index |
| LiveCodeBench (Vals AI)Coding | 83.2% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 33.6% | 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 | 94.8% | Not in index |
| MGSM (Vals AI)Math | 92.0% | Not in index |
| SAGE (Vals AI)General | Not measured | Not in index |
| LegalBench (Vals AI)Knowledge | 75.9% | Not in index |
| CaseLaw (Vals AI)Knowledge | 48.8% | Not in index |
| CorpFin (Vals AI)Knowledge | 58.2% | Not in index |
| TaxEval (Vals AI)Knowledge | 71.6% | Not in index |
| MortgageTax (Vals AI)Knowledge | Not measured | Not in index |
| MedQA (Vals AI)Knowledge | 91.4% | 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 | 93.4 | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | 78.2% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 19.6% | Not in index |
| MMLU Pro (Artificial Analysis run)Knowledge | 80.8% | Not in index |
| LiveCodeBench (Artificial Analysis run)Coding | 87.8% | Not in index |
| SciCodeCoding | 34.0% | Not in index |
| Terminal-Bench Hard (Artificial Analysis run)Coding | 23.5% | Not in index |
| IFBenchGeneral | 69.0% | Not in index |
| Long context reasoning (AA-LCR)General | 52.0% | Not in index |
| τ²-Bench TelecomAgentic work | 65.8% | Not in index |
| AIME 2025 (Artificial Analysis run)Math | 93.4% | Not in index |
| Terminal-BenchCoding | 18.7% | 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 | 48.2% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 4.4% | Not in index |
| METR time horizonsAgentic work | 56.6% | 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 | 22.1% | Not in index |
| Chess puzzlesReasoning | Not measured | Not in index |
| Mystery game puzzlesReasoning | 2.0% | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 88.9% | 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 | Not measured | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 76.3% | Not in index |
| LMCAGeneral | 22.1% | Not in index |
| Fiction.LiveBenchGeneral | 44.4% | Not in index |
| Creative writing (Lech Mazur)General | 77.1% | Not in index |
| CL-benchGeneral | Not measured | Not in index |
| Surface Evolver BenchGeneral | 25.0% | 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 | 575.6 | Not in index |
| Vending-Bench 2Agentic work | -$22 | Not in index |
| Epoch Capabilities IndexIntelligence | 140.0 | Not in index |
| LMArena TextGeneral | 1366 | Not in index |
| LMArena Text: codingCoding | 1379 | Not in index |
| LMArena Text: hard promptsReasoning | 1363 | Not in index |
| LMArena Text: mathMath | 1389 | Not in index |
| LMArena Text: instruction followingGeneral | 1318 | Not in index |
| LMArena Text: creative writingGeneral | 1275 | Not in index |
| LMArena VisionGeneral | Not measured | Not in index |
| LMArena Text: EnglishGeneral | 1375 | Not in index |
| LMArena Text: non-EnglishGeneral | 1351 | Not in index |
| LMArena Text: ChineseGeneral | 1385 | Not in index |
| LMArena Text: GermanGeneral | 1354 | Not in index |
| LMArena Text: JapaneseGeneral | 1330 | Not in index |
| LMArena Text: KoreanGeneral | 1283 | Not in index |
| LMArena Text: FrenchGeneral | 1369 | Not in index |
| LMArena Text: SpanishGeneral | 1389 | Not in index |
| LMArena Text: RussianGeneral | 1343 | Not in index |
| LMArena Text: PolishGeneral | 1353 | Not in index |
| LMArena Text: multi-turnGeneral | 1340 | Not in index |
| LMArena Text: longer queriesGeneral | 1319 | Not in index |
| LMArena Text: expertReasoning | 1356 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1368 | Not in index |
| LMArena Text: software and ITCoding | 1388 | Not in index |
| LMArena Text: mathematical workMath | 1386 | Not in index |
| LMArena Text: scienceKnowledge | 1382 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1388 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1354 | Not in index |
| LMArena Text: business and financeKnowledge | 1359 | Not in index |
| LMArena Text: writing and languageGeneral | 1306 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1292 | Not in index |
| LMArena WebDev: ReactCoding | Not measured | Not in index |
| LMArena WebDev: HTMLCoding | Not measured | Not in index |
| LMArena WebDev: from an imageCoding | Not measured | Not in index |
| LMArena Vision: EnglishGeneral | Not measured | Not in index |
| LMArena Vision: ChineseGeneral | Not measured | Not in index |
| LMArena Vision: reading textGeneral | Not measured | Not in index |
| LMArena Vision: diagramsReasoning | Not measured | 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.
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 |
|---|---|---|---|
| Aider polyglot | 41.8% | $0.74 of the run | Solved on the first try 13.8% · Edits well formed 79.1% · Time per exercise 36 s · Input tokens, whole run 3.1M · Output tokens, whole run 856,495 |
| SWE-bench Verified | 26.0% | $0.0571 per attempt | Nothing else |
| SWE-bench Verified (Vals AI) | 33.6% | $0.17 per test | Duration, as printed 4m 16s |
| WeirdML | 48.2% | $0.0335 per run | Median lines of code 255 |
| Surface Evolver Bench | 25.0% | $0.0892 of the run | Pass rate 6.3% · Tokens for the run 1.5M |
| ALE-Bench | 575.6 | $0.0013 per problem | Tokens per problem 5,041 |
| GPQA Diamond | 78.5% | Not published | Latency, as printed 56 s |
| AIME | 92.6% | Not published | Latency, as printed 2m 37s |
| MMLU Pro | 79.2% | Not published | Latency, as printed 35 s |
| Design Arena: websites | 968 Elo | Not published | Battles 4,144 |
| Design Arena: UI components | 927 Elo | Not published | Battles 269 |
| Design Arena: game dev | 992 Elo | Not published | Battles 445 |
| Design Arena: data viz | 987 Elo | Not published | Battles 101 |
|---|---|---|---|
| Design Arena: 3D | 901 Elo | Not published | Battles 313 |
| Design Arena: all code categories | 963 Elo | Not published | Battles 5,272 |
| LiveCodeBench (Vals AI) | 83.2% | Not published | Latency, as printed 1m 22s |
| MATH 500 (Vals AI) | 94.8% | Not published | Latency, as printed 16 s |
| MGSM (Vals AI) | 92.0% | Not published | Latency, as printed 5.8 s |
| LegalBench (Vals AI) | 75.9% | Not published | Latency, as printed 7.8 s |
| CaseLaw (Vals AI) | 48.8% | Not published | Latency, as printed 1m 08s |
| CorpFin (Vals AI) | 58.2% | Not published | Latency, as printed 43 s |
| TaxEval (Vals AI) | 71.6% | Not published | Latency, as printed 48 s |
| MedQA (Vals AI) | 91.4% | Not published | Latency, as printed 12 s |
| APEX-Agents | 4.4% | Not published | Mean score 8.3% |
| LMArena Text | 1366 Elo | Not published | Votes 30,206 · Interval (±) ±4.3 |
| LMArena Text: coding | 1379 Elo | Not published | Votes 6,410 · Interval (±) ±7.7 |
| LMArena Text: hard prompts | 1363 Elo | Not published | Votes 14,685 · Interval (±) ±5.6 |
| LMArena Text: math | 1389 Elo | Not published | Votes 1,780 · Interval (±) ±13.8 |
| LMArena Text: instruction following | 1318 Elo | Not published | Votes 7,865 · Interval (±) ±7.0 |
| LMArena Text: creative writing | 1275 Elo | Not published | Votes 3,908 · Interval (±) ±9.7 |
| LMArena Text: English | 1375 Elo | Not published | Votes 13,030 · Interval (±) ±5.9 |
| LMArena Text: non-English | 1351 Elo | Not published | Votes 17,137 · Interval (±) ±5.3 |
| LMArena Text: Chinese | 1385 Elo | Not published | Votes 2,276 · Interval (±) ±12.6 |
| LMArena Text: German | 1354 Elo | Not published | Votes 671 · Interval (±) ±22.7 |
| LMArena Text: Japanese | 1330 Elo | Not published | Votes 574 · Interval (±) ±25.4 |
| LMArena Text: Korean | 1283 Elo | Not published | Votes 680 · Interval (±) ±23.7 |
| LMArena Text: French | 1369 Elo | Not published | Votes 460 · Interval (±) ±28.0 |
| LMArena Text: Spanish | 1389 Elo | Not published | Votes 855 · Interval (±) ±21.2 |
| LMArena Text: Russian | 1343 Elo | Not published | Votes 2,144 · Interval (±) ±12.5 |
| LMArena Text: Polish | 1353 Elo | Not published | Votes 1,733 · Interval (±) ±14.5 |
| LMArena Text: multi-turn | 1340 Elo | Not published | Votes 4,883 · Interval (±) ±8.7 |
| LMArena Text: longer queries | 1319 Elo | Not published | Votes 6,565 · Interval (±) ±7.7 |
| LMArena Text: expert | 1356 Elo | Not published | Votes 1,403 · Interval (±) ±15.7 |
| LMArena Text: hard prompts in English | 1368 Elo | Not published | Votes 6,482 · Interval (±) ±7.7 |
| LMArena Text: software and IT | 1388 Elo | Not published | Votes 10,219 · Interval (±) ±6.4 |
| LMArena Text: mathematical work | 1386 Elo | Not published | Votes 1,550 · Interval (±) ±14.7 |
| LMArena Text: science | 1382 Elo | Not published | Votes 4,830 · Interval (±) ±8.8 |
| LMArena Text: medicine and healthcare | 1388 Elo | Not published | Votes 1,624 · Interval (±) ±15.0 |
| LMArena Text: legal and government | 1354 Elo | Not published | Votes 1,874 · Interval (±) ±13.7 |
| LMArena Text: business and finance | 1359 Elo | Not published | Votes 5,361 · Interval (±) ±8.4 |
| LMArena Text: writing and language | 1306 Elo | Not published | Votes 6,642 · Interval (±) ±7.6 |
| LMArena Text: entertainment and media | 1292 Elo | Not published | Votes 5,492 · Interval (±) ±8.1 |