As of October 20, 2026, Z.ai GLM 5.3 ranks #15 of 213 models overall with 44.8 on the Artificial Analysis Intelligence Index. Its strongest category is agentic, where it ranks #5 of 87. Z.ai GLM 5.3 costs $0.079 per million input tokens and $1.40 per million output tokens. It was released on August 18, 2026.
Its output price ranks 163 of 349 priced models, counting from the cheapest.
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
z-ai/glm-5.3 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, SWE-bench Multimodal (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, GSO-Bench, MirrorCode, Cybench, LMArena Text: coding, LMArena Text: software and IT, 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 Android apps, Design Arena: agents building Godot games, Design Arena: agents building games, Design Arena: spreadsheets, 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, Remote Labor Index, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, PostTrainBench, TheAgentCompany, OSWorld, SpireClimb, LMArena Search
Not measured on MMMU Pro (Vals AI), ARC-AGI, ARC-AGI-2, Humanity's Last Exam, SimpleBench, EBR-bench, VPCT, BIG-Bench Hard, LMArena Text: hard prompts, LMArena Text: expert, LMArena Text: hard prompts in English, 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, LMArena Text: math, LMArena Text: mathematical work
Not measured on CaseLaw (Vals AI), CorpFin (Vals AI), MortgageTax (Vals AI), MedQA (Vals AI), MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge, LMArena Text: science, LMArena Text: medicine and healthcare, LMArena Text: legal and government, LMArena Text: business and finance
Not measured on SAGE (Vals AI), Vals Multimodal Index, IFBench, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, Surface Evolver Bench, Furniture assembly, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, LMArena Text, LMArena Text: instruction following, LMArena Text: creative writing, LMArena Vision, LMArena Text: English, LMArena Text: non-English, LMArena Text: Chinese, LMArena Text: German, LMArena Text: Japanese, LMArena Text: Korean, LMArena Text: French, LMArena Text: Spanish, LMArena Text: Russian, LMArena Text: Polish, LMArena Text: multi-turn, LMArena Text: longer queries, LMArena Text: writing and language, LMArena Text: entertainment and media, 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 | 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 | 82.8% | 20% |
| LMArena WebDevCoding | 1621 | 15% |
| Vals IndexGeneral | 59.7% | Not in index |
| GPQA DiamondReasoning | 88.1% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 86.8% | Not in index |
| AA Intelligence IndexIntelligence | 44.8 | Not in index |
| AA Coding IndexCoding | 74.8 | Not in index |
| AA Agentic IndexAgentic work | 53.1 | Not in index |
| Design Arena: websitesWeb design | 1295 | Not in index |
| Design Arena: UI componentsWeb design | 1314 | Not in index |
| Design Arena: game devWeb design | 1312 | Not in index |
| Design Arena: data vizWeb design | 1258 | Not in index |
| Design Arena: 3DWeb design | 1334 | Not in index |
| Design Arena: all code categoriesWeb design | 1304 | Not in index |
| Design Arena: SVGWeb design | 1293 | Not in index |
| Design Arena: ASCII artWeb design | 1211 | 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 | 1193 | 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 | 1189 | Not in index |
| Design Arena: PowerPoint slidesAgentic work | 1255 | 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 | 85.8% | Not in index |
| LiveBench data analysisGeneral | 70.2% | Not in index |
| LiveBench researchAgentic work | 73.2% | Not in index |
| LiveBench browserAgentic work | 0.0% | Not in index |
| LiveBench long agenticAgentic work | 35.9% | Not in index |
| LiveBench designWeb design | 77.3% | Not in index |
| LiveCodeBench (Vals AI)Coding | 80.5% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 95.4% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 38.9% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 78.1% | Not in index |
| Code migration (Vals AI)Coding | 44.2% | Not in index |
| ProgramBench (Vals AI)Coding | 1.5% | Not in index |
| SREBench (Vals AI)Agentic work | 9.2% | Not in index |
| IOI (Vals AI)Coding | 68.4% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 71.5% | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | Not measured | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | 20.0% | Not in index |
| SkillsBench (Vals AI)Coding | 47.5% | Not in index |
| CyberBench (Vals AI)Coding | 72.1% | Not in index |
| Finance Agent (Vals AI)Agentic work | 55.8% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 39.7% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 49.0% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | 14.6% | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 56.3% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | Not measured | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 5.7% | 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 | 68.5% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | 23.0% | 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 | 84.8% | 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 | 72.4% | 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 | 42.9% | Not in index |
| MedScribe (Vals AI)General | 88.8% | 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 | 91.7% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 42.3% | 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 | 59.0% | 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 | 79.7% | 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 | 69.0% | Not in index |
| FrontierCodeCoding | 40.1% | Not in index |
| FrontierSWECoding | 30.2% | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | 75.4% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 56.6% | 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 | Not measured | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 90.9% | 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 | Not measured | Not in index |
| Chess puzzlesReasoning | 37.0% | Not in index |
| Mystery game puzzlesReasoning | 33.0% | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 91.1% | Not in index |
| FrontierMath, tiers 1 to 3Math | 68.8% | Not in index |
| FrontierMath, tier 4Math | 29.3% | Not in index |
| ProofBenchMath | 49.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 41.0% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 87.7% | Not in index |
| LMCAGeneral | 55.5% | 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 | 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 | 1317.4 | Not in index |
| Vending-Bench 2Agentic work | $8,164 | Not in index |
| Epoch Capabilities IndexIntelligence | 155.9 | Not in index |
| LMArena TextGeneral | Not measured | Not in index |
| LMArena Text: codingCoding | Not measured | Not in index |
| LMArena Text: hard promptsReasoning | Not measured | Not in index |
| LMArena Text: mathMath | Not measured | Not in index |
| LMArena Text: instruction followingGeneral | Not measured | Not in index |
| LMArena Text: creative writingGeneral | Not measured | Not in index |
| LMArena VisionGeneral | Not measured | Not in index |
| LMArena Text: EnglishGeneral | Not measured | Not in index |
| LMArena Text: non-EnglishGeneral | Not measured | Not in index |
| LMArena Text: ChineseGeneral | Not measured | 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 | Not measured | Not in index |
| LMArena Text: SpanishGeneral | Not measured | Not in index |
| LMArena Text: RussianGeneral | Not measured | Not in index |
| LMArena Text: PolishGeneral | Not measured | Not in index |
| LMArena Text: multi-turnGeneral | Not measured | Not in index |
| LMArena Text: longer queriesGeneral | Not measured | Not in index |
| LMArena Text: expertReasoning | Not measured | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | Not measured | Not in index |
| LMArena Text: software and ITCoding | Not measured | Not in index |
| LMArena Text: mathematical workMath | Not measured | Not in index |
| LMArena Text: scienceKnowledge | Not measured | Not in index |
| LMArena Text: medicine and healthcareKnowledge | Not measured | Not in index |
| LMArena Text: legal and governmentKnowledge | Not measured | Not in index |
| LMArena Text: business and financeKnowledge | Not measured | Not in index |
| LMArena Text: writing and languageGeneral | Not measured | Not in index |
| LMArena Text: entertainment and mediaGeneral | Not measured | Not in index |
| LMArena WebDev: ReactCoding | 1641 | Not in index |
| LMArena WebDev: HTMLCoding | 1595 | 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 |
|---|---|---|---|
| LiveBench coding | 82.8% | $2.1384 per task | Output tokens per task 45,039 |
| Vals Index | 59.7% | $8.52 per test | Duration, as printed 1h 04m |
| LiveBench reasoning | 85.8% | $0.2648 per task | Output tokens per task 59,828 |
| LiveBench data analysis | 70.2% | $0.3731 per task | Output tokens per task 83,548 |
| LiveBench research | 73.2% | $1.6346 per task | Output tokens per task 78,992 |
| LiveBench long agentic | 35.9% | $18.3819 per task | Output tokens per task 443,888 |
| LiveBench design | 77.3% | $0.9556 per task | Output tokens per task 68,015 |
| SWE-bench Verified (Vals AI) | 95.4% | $0.34 per test | Duration, as printed 14m 01s |
| Terminal-Bench 4 (Vals AI) | 38.9% | $9.37 per test | Duration, as printed 1h 23m |
| Vibe Code Bench (Vals AI) | 78.1% | $12.45 per test | Duration, as printed 1h 04m |
| Code migration (Vals AI) | 44.2% | $24.91 per test | Duration, as printed 3h 47m |
| ProgramBench (Vals AI) | 1.5% | $21.96 per test | Duration, as printed 4h 16m |
| SREBench (Vals AI) | 9.2% | $27.47 per test | Duration, as printed 2h 48m |
|---|---|---|---|
| IOI (Vals AI) | 68.4% | $7.67 per test | Duration, as printed 1h 46m |
| Terminal-Bench 2.1 (Vals AI) | 71.5% | $0.31 per test | Duration, as printed 13m 07s |
| Vibe Code Bench 1-100 (Vals AI) | 20.0% | $8.24 per test | Duration, as printed 1h 26m |
| SkillsBench (Vals AI) | 47.5% | $0.71 per test | Duration, as printed 13m 07s |
| CyberBench (Vals AI) | 72.1% | $2.69 per test | Duration, as printed 30m 18s |
| Finance Agent (Vals AI) | 55.8% | $1.07 per test | Duration, as printed 15m 50s |
| Tax Agent Bench (Vals AI) | 39.7% | $1.80 per test | Duration, as printed 50m 53s |
| Legal Research Bench (Vals AI) | 49.0% | $2.24 per test | Duration, as printed 51m 50s |
| Harvey's Legal Agent Benchmark (Vals AI) | 14.6% | $3.99 per test | Duration, as printed 31m 51s |
| Excel Modeling Benchmark (Vals AI) | 56.3% | $3.79 per test | Duration, as printed 36m 12s |
| Terminal-Bench-Science (Vals AI) | 5.7% | $15.63 per test | Duration, as printed 2h 45m |
| Public Benefits Bench (Vals AI) | 68.5% | $0.95 per test | Nothing else |
| MysteryMechanism (Vals AI) | 23.0% | $1.53 per test | Duration, as printed 30m 42s |
| DeepSWE | 69.0% | $3.9934 mean cost per task | Solved in 4 tries 87.6% · Output tokens per task 80,436 · Agent steps per task 124 |
| FrontierSWE | 30.2% | $97.22 average cost per task | Best of 5 runs 40.6% · Hours per task 17.0 h |
| WeirdML | 75.4% | $0.5351 per run | Median lines of code 244 |
| ProofBench | 49.0% | $2.0815 per test | Time per proof 42m 23s |
| ALE-Bench | 1317.4 | $0.284 per problem | Tokens per problem 67,123 |
| LMArena WebDev | 1621 Elo | Not published | Votes 9,828 · Interval (±) ±7.5 |
| GPQA Diamond | 88.1% | Not published | Latency, as printed 3m 31s |
| MMLU Pro | 86.8% | Not published | Latency, as printed 1m 02s |
| Design Arena: agents building mobile apps | 1193 Elo | Not published | Battles 301 |
| Design Arena: PowerPoint slides | 1255 Elo | Not published | Battles 248 |
| LiveCodeBench (Vals AI) | 80.5% | Not published | Latency, as printed 4m 07s |
| LegalBench (Vals AI) | 84.8% | Not published | Latency, as printed 22 s |
| TaxEval (Vals AI) | 72.4% | Not published | Latency, as printed 1m 38s |
| MedCode (Vals AI) | 42.9% | Not published | Latency, as printed 2m 49s |
| MedScribe (Vals AI) | 88.8% | Not published | Latency, as printed 2m 02s |
| APEX-Agents | 56.6% | Not published | Mean score 66.2% |
| LMArena WebDev: React | 1641 Elo | Not published | Votes 6,344 · Interval (±) ±9.0 |
| LMArena WebDev: HTML | 1595 Elo | Not published | Votes 1,304 · Interval (±) ±17.9 |