As of October 21, 2026, Z.ai GLM 5.2 ranks #33 of 123 models overall with 62.5 ±7.1 on the LLMBenchmark Index. GLM 5.2 ranks #26 of 133 in web design, its strongest category. Z.ai GLM 5.2 costs $1.40 per million input tokens and $4.40 per million output tokens. GLM 5.2 was released on June 16, 2026.
GLM 5.2's output price ranks 249 of 349 priced models, counting from the cheapest.
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
z-ai/glm-5.2 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 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), Terminal-Bench, DeepSWE, FrontierSWE, GSO-Bench, MirrorCode, Cybench, LMArena WebDev: from an image, SciCode
Not measured on Design Arena: spreadsheets, LiveBench research, LiveBench browser, LiveBench long agentic, Tax Agent Bench (Vals AI), Harvey's Legal Agent 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), METR time horizons, Remote Labor Index, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, TheAgentCompany, OSWorld, SpireClimb, LMArena Search, Berkeley Function Calling Leaderboard (BFCL), BrowseComp-Plus
Not measured on LiveBench reasoning, MysteryMechanism (Vals AI), MMMU Pro (Vals AI), Humanity's Last Exam, VPCT, BIG-Bench Hard, LMArena Vision: diagrams, LMArena Vision: homework
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), MortgageTax (Vals AI), MedQA (Vals AI), MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge, FACTS Benchmark Suite
Not measured on LiveBench design
Not measured on Vals Index, LiveBench data analysis, Public Benefits Bench (Vals AI), SAGE (Vals AI), Vals Multimodal Index, Fiction.LiveBench, Creative writing (Lech Mazur), 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 | 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 | Not measured | 15% |
| LMArena WebDevCoding | 1604 | 10% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 85.6% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 86.7% | Not in index |
| AA Intelligence IndexIntelligence | 33.7 | Not in index |
| AA Coding IndexCoding | 68.8 | Not in index |
| AA Agentic IndexAgentic work | 38.4 | Not in index |
| Design Arena: websitesWeb design | 1285 | Not in index |
| Design Arena: UI componentsWeb design | 1296 | Not in index |
| Design Arena: game devWeb design | 1268 | Not in index |
| Design Arena: data vizWeb design | 1285 | Not in index |
| Design Arena: 3DWeb design | 1288 | Not in index |
| Design Arena: all code categoriesWeb design | 1288 | Not in index |
| Design Arena: SVGWeb design | 1214 | Not in index |
| Design Arena: ASCII artWeb design | 1190 | Not in index |
| Design Arena: agents building web appsAgentic work | 1222 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1241 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1160 | Not in index |
| Design Arena: agents building Android appsAgentic work | 1178 | Not in index |
| Design Arena: agents building Godot gamesAgentic work | 1142 | Not in index |
| Design Arena: agents building gamesAgentic work | 1206 | Not in index |
| Design Arena: HTML slidesAgentic work | 1175 | Not in index |
| Design Arena: PowerPoint slidesAgentic work | 1195 | 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 | 69.5% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 82.8% | 15% |
| Terminal-Bench 4 (Vals AI)Coding | Not measured | 25% |
| Vibe Code Bench (Vals AI)Coding | 64.0% | 20% |
| Code migration (Vals AI)Coding | 37.9% | Not in index |
| ProgramBench (Vals AI)Coding | 0.5% | Not in index |
| SREBench (Vals AI)Agentic work | 0.0% | Not in index |
| IOI (Vals AI)Coding | Not measured | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 67.8% | 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 | 45.1% | Not in index |
| CyberBench (Vals AI)Coding | Not measured | Not in index |
| Finance Agent (Vals AI)Agentic work | 49.7% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | Not measured | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 31.3% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 61.5% | 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 | 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 | Not measured | Not in index |
| LegalBench (Vals AI)Knowledge | 84.1% | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | 66.1% | Not in index |
| TaxEval (Vals AI)Knowledge | 73.3% | 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 | 40.8% | Not in index |
| MedScribe (Vals AI)General | 83.5% | 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 | 89.5% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 41.1% | 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 | 51.2% | Not in index |
| Terminal-Bench Hard (Artificial Analysis run)Coding | 50.8% | Not in index |
| IFBenchGeneral | 73.3% | Not in index |
| Long context reasoning (AA-LCR)General | 78.3% | Not in index |
| τ²-Bench TelecomAgentic work | 99.1% | 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 | 24.5% | 15% |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | 70.1% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 45.2% | 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 | 31.7% | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 91.9% | Not in index |
| ARC-AGIReasoning | 77.0% | Not in index |
| ARC-AGI-2Reasoning | 22.8% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | 58.8% | Not in index |
| Chess puzzlesReasoning | 22.0% | Not in index |
| Mystery game puzzlesReasoning | 19.0% | Not in index |
| EBR-benchReasoning | 9.5% | Not in index |
| OTIS Mock AIMEMath | 86.4% | Not in index |
| FrontierMath, tiers 1 to 3Math | 59.2% | Not in index |
| FrontierMath, tier 4Math | 29.3% | Not in index |
| ProofBenchMath | 35.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 34.2% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 93.6% | Not in index |
| LMCAGeneral | 45.8% | 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 | 55.6% | 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 | 1047.0 | Not in index |
| Vending-Bench 2Agentic work | $8,314 | Not in index |
| Epoch Capabilities IndexIntelligence | 151.9 | Not in index |
| LMArena TextGeneral | 1470 | Not in index |
| LMArena Text: codingCoding | 1487 | Not in index |
| LMArena Text: hard promptsReasoning | 1481 | Not in index |
| LMArena Text: mathMath | 1483 | Not in index |
| LMArena Text: instruction followingGeneral | 1466 | Not in index |
| LMArena Text: creative writingGeneral | 1463 | Not in index |
| LMArena VisionGeneral | Not measured | Not in index |
| LMArena Text: EnglishGeneral | 1475 | Not in index |
| LMArena Text: non-EnglishGeneral | 1459 | Not in index |
| LMArena Text: ChineseGeneral | 1522 | Not in index |
| LMArena Text: GermanGeneral | 1470 | Not in index |
| LMArena Text: JapaneseGeneral | 1450 | Not in index |
| LMArena Text: KoreanGeneral | 1440 | Not in index |
| LMArena Text: FrenchGeneral | 1479 | Not in index |
| LMArena Text: SpanishGeneral | 1478 | Not in index |
| LMArena Text: RussianGeneral | 1468 | Not in index |
| LMArena Text: PolishGeneral | 1456 | Not in index |
| LMArena Text: multi-turnGeneral | 1469 | Not in index |
| LMArena Text: longer queriesGeneral | 1480 | Not in index |
| LMArena Text: expertReasoning | 1487 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1481 | Not in index |
| LMArena Text: software and ITCoding | 1486 | Not in index |
| LMArena Text: mathematical workMath | 1489 | Not in index |
| LMArena Text: scienceKnowledge | 1489 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1475 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1486 | Not in index |
| LMArena Text: business and financeKnowledge | 1451 | Not in index |
| LMArena Text: writing and languageGeneral | 1463 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1450 | Not in index |
| LMArena WebDev: ReactCoding | 1617 | Not in index |
| LMArena WebDev: HTMLCoding | 1565 | 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 |
| Berkeley Function Calling Leaderboard (BFCL)Agentic work | Not measured | Not in index |
| Kagi LLM BenchmarkReasoning | 62.6% | Not in index |
| BrowseComp-PlusAgentic work | Not measured | Not in index |
| SciCodeCoding | Not measured | Not in index |
| FACTS Benchmark SuiteKnowledge | 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 |
|---|---|---|---|
| SWE-bench Verified (Vals AI) | 82.8% | $0.71 per test | Duration, as printed 11m 10s |
| Vibe Code Bench (Vals AI) | 64.0% | $8.49 per test | Duration, as printed 1h 02m |
| Code migration (Vals AI) | 37.9% | $12.64 per test | Duration, as printed 1h 54m |
| ProgramBench (Vals AI) | 0.5% | $12.58 per test | Duration, as printed 2h 06m |
| SREBench (Vals AI) | 0.0% | $26.58 per test | Duration, as printed 2h 29m |
| Terminal-Bench 2.1 (Vals AI) | 67.8% | $0.43 per test | Duration, as printed 13m 41s |
| SkillsBench (Vals AI) | 45.1% | $0.81 per test | Duration, as printed 19m 52s |
| Finance Agent (Vals AI) | 49.7% | $0.71 per test | Duration, as printed 7m 53s |
| Legal Research Bench (Vals AI) | 31.3% | $0.89 per test | Duration, as printed 17m 03s |
| Excel Modeling Benchmark (Vals AI) | 61.5% | $4.47 per test | Duration, as printed 58m 52s |
| WeirdML | 70.1% | $0.5073 per run | Median lines of code 200 |
| ARC-AGI | 77.0% | $0.1916 per task | Nothing else |
| ARC-AGI-2 | 22.8% | $0.2501 per task | Nothing else |
|---|---|---|---|
| ProofBench | 35.0% | $0.00 per test | Time per proof 0.0 s |
| Surface Evolver Bench | 55.6% | $4.6462 of the run | Pass rate 31.3% · Tokens for the run 2.5M |
| ALE-Bench | 1047.0 | $0.1577 per problem | Tokens per problem 38,099 |
| Kagi LLM Benchmark | 62.6% | $0.70 of the suite | Nothing else |
| LMArena WebDev | 1604 Elo | Not published | Votes 16,657 · Interval (±) ±6.0 |
| GPQA Diamond | 85.6% | Not published | Latency, as printed 3m 45s |
| MMLU Pro | 86.7% | Not published | Latency, as printed 52 s |
| Design Arena: websites | 1285 Elo | Not published | Battles 35,662 |
| Design Arena: UI components | 1296 Elo | Not published | Battles 1,845 |
| Design Arena: game dev | 1268 Elo | Not published | Battles 7,880 |
| Design Arena: data viz | 1285 Elo | Not published | Battles 3,753 |
| Design Arena: 3D | 1288 Elo | Not published | Battles 7,904 |
| Design Arena: all code categories | 1288 Elo | Not published | Battles 56,907 |
| Design Arena: SVG | 1214 Elo | Not published | Battles 2,165 |
| Design Arena: ASCII art | 1190 Elo | Not published | Battles 583 |
| Design Arena: agents building web apps | 1222 Elo | Not published | Battles 6,333 |
| Design Arena: agents building full-stack apps | 1241 Elo | Not published | Battles 2,760 |
| Design Arena: agents building mobile apps | 1160 Elo | Not published | Battles 1,876 |
| Design Arena: agents building Android apps | 1178 Elo | Not published | Battles 1,534 |
| Design Arena: agents building games | 1206 Elo | Not published | Battles 855 |
| Design Arena: HTML slides | 1175 Elo | Not published | Battles 1,881 |
| Design Arena: PowerPoint slides | 1195 Elo | Not published | Battles 1,177 |
| LiveCodeBench (Vals AI) | 69.5% | Not published | Latency, as printed 8m 52s |
| LegalBench (Vals AI) | 84.1% | Not published | Latency, as printed 5.8 s |
| CorpFin (Vals AI) | 66.1% | Not published | Latency, as printed 25 s |
| TaxEval (Vals AI) | 73.3% | Not published | Latency, as printed 1m 05s |
| MedCode (Vals AI) | 40.8% | Not published | Latency, as printed 1m 35s |
| MedScribe (Vals AI) | 83.5% | Not published | Latency, as printed 2m 18s |
| APEX-Agents | 45.2% | Not published | Mean score 61.1% |
| LMArena Text | 1470 Elo | Not published | Votes 51,221 · Interval (±) ±4.1 |
| LMArena Text: coding | 1487 Elo | Not published | Votes 13,716 · Interval (±) ±6.1 |
| LMArena Text: hard prompts | 1481 Elo | Not published | Votes 33,290 · Interval (±) ±4.7 |
| LMArena Text: math | 1483 Elo | Not published | Votes 2,303 · Interval (±) ±12.4 |
| LMArena Text: instruction following | 1466 Elo | Not published | Votes 17,693 · Interval (±) ±5.6 |
| LMArena Text: creative writing | 1463 Elo | Not published | Votes 10,217 · Interval (±) ±6.9 |
| LMArena Text: English | 1475 Elo | Not published | Votes 20,996 · Interval (±) ±5.2 |
| LMArena Text: non-English | 1459 Elo | Not published | Votes 30,215 · Interval (±) ±4.7 |
| LMArena Text: Chinese | 1522 Elo | Not published | Votes 3,696 · Interval (±) ±10.3 |
| LMArena Text: German | 1470 Elo | Not published | Votes 913 · Interval (±) ±20.2 |
| LMArena Text: Japanese | 1450 Elo | Not published | Votes 835 · Interval (±) ±22.4 |
| LMArena Text: Korean | 1440 Elo | Not published | Votes 988 · Interval (±) ±19.9 |
| LMArena Text: French | 1479 Elo | Not published | Votes 1,902 · Interval (±) ±15.1 |
| LMArena Text: Spanish | 1478 Elo | Not published | Votes 1,548 · Interval (±) ±15.8 |
| LMArena Text: Russian | 1468 Elo | Not published | Votes 6,017 · Interval (±) ±8.2 |
| LMArena Text: Polish | 1456 Elo | Not published | Votes 834 · Interval (±) ±20.6 |
| LMArena Text: multi-turn | 1469 Elo | Not published | Votes 8,108 · Interval (±) ±7.3 |
| LMArena Text: longer queries | 1480 Elo | Not published | Votes 23,394 · Interval (±) ±5.3 |
| LMArena Text: expert | 1487 Elo | Not published | Votes 5,377 · Interval (±) ±8.6 |
| LMArena Text: hard prompts in English | 1481 Elo | Not published | Votes 13,844 · Interval (±) ±6.0 |
| LMArena Text: software and IT | 1486 Elo | Not published | Votes 19,889 · Interval (±) ±5.4 |
| LMArena Text: mathematical work | 1489 Elo | Not published | Votes 2,786 · Interval (±) ±11.6 |
| LMArena Text: science | 1489 Elo | Not published | Votes 8,550 · Interval (±) ±7.1 |
| LMArena Text: medicine and healthcare | 1475 Elo | Not published | Votes 3,768 · Interval (±) ±10.3 |
| LMArena Text: legal and government | 1486 Elo | Not published | Votes 4,161 · Interval (±) ±9.8 |
| LMArena Text: business and finance | 1451 Elo | Not published | Votes 9,744 · Interval (±) ±6.7 |
| LMArena Text: writing and language | 1463 Elo | Not published | Votes 13,740 · Interval (±) ±6.1 |
| LMArena Text: entertainment and media | 1450 Elo | Not published | Votes 12,713 · Interval (±) ±6.4 |
| LMArena WebDev: React | 1617 Elo | Not published | Votes 11,346 · Interval (±) ±7.0 |
| LMArena WebDev: HTML | 1565 Elo | Not published | Votes 2,032 · Interval (±) ±14.6 |