Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Z.AI · Open Weight · rank 38 · bench-align-v5
GLM-5.3 is built for coding and reasoning. It ranks in the top quarter for reasoning (top 17% of 216 scored models) and coding (top 24% of 210 scored models), by BenchLM's published scores. It accepts text and produces text.
Every published price component, including cache reads and writes.
Lifecycle events the source associates with this model, plus what this profile does not claim.
That is not evidence the model has no lifecycle plan — only that this source published none.
GLM-5.3 by Z.AI scores 63.7 overall and carries a context window of 1M tokens — observed 2026-11-21.
Seven axes from the ranking source. A missing axis is drawn as a gap.
Each axis shows the ranking source’s score and, beside it, BenchLM’s separate verified score for that axis. The two are published side by side and are not interchangeable.
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: Observed
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | 67.58 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 86 tok/s | 2026-11-21 | 2026-11-21 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 31.6 | #55 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-GPQA Diamond Artificial Analysis GPQA Diamond | 91.7 | #25 | Graduate-level science questions | Graduate-level science reasoning | Artificial Analysis GPQA Diamond Benchmark Leaderboard |
| AA-HLE Artificial Analysis Humanity's Last Exam | 42.3 | #39 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | 6.0 | #55 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 32.3 | #83 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 38.9 | #168 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| GPQA Diamond (Vals) GPQA Diamond, Vals AI run | 88.1 | #35 | Graduate-level science questions | Expert reasoning | Vals AI GPQA Diamond, Vals AI run leaderboard |
| MMLU-Pro (Vals) MMLU-Pro, Vals AI run | 86.8 | #34 | Academic multiple-choice questions | Broad academic knowledge | Vals AI MMLU-Pro, Vals AI run leaderboard |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 Terminal-Bench 2.1 | 88.2 | #9 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| VulcanBench v3 VulcanBench v3 | 78.3 | #12 | 23 post-cutoff repository tasks in the v3 report | Professional multi-file software engineering | VulcanBench |
| OpenHarmony Bench v1.0 OpenHarmony Bench v1.0 | 60.8 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3) FrontierMath v2 Tiers 1-3 | 68.772 | #29 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | FrontierMath v2 benchmark hub |
| FrontierMath v2 (Tier 4) FrontierMath v2 Tier 4 | 29.268 | #32 | 41 private extreme-difficulty mathematics problems | Research-level mathematics requiring hours or days of expert work | FrontierMath Tier 4 v2 leaderboard |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-LCR Artificial Analysis Long Context Reasoning | 79.7 | #48 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| MLCR-AA Medical Long Context Reasoning (MLCR-AA) | 17.2 | #36 | Long, fragmented medical-record reasoning | Long-context medical reasoning | Medical Long Context Reasoning (MLCR-AA) |
| CritPt Critical Physics Tasks | 19.1 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA Briefcase Artificial Analysis Briefcase | 1501 | #26 | Professional knowledge-work tasks | Professional work | Artificial Analysis Briefcase Benchmark Leaderboard |
| AA AutomationBench Artificial Analysis AutomationBench | 62.2 | #19 | Business-process automation tasks | Agentic automation | Artificial Analysis AutomationBench Benchmark Leaderboard |
| AA EnterpriseOps-Gym Artificial Analysis EnterpriseOps-Gym | 36.4 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Design Arena Website Design Arena Website Elo | 1275 | #26 | Website generation comparisons | Design and website generation | OpenRouter Grok 4.3 benchmarks |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| ExploitBench ExploitBench v8-bench | 54 | #12 | V8 exploit synthesis runs | Browser exploitation and cybersecurity | ExploitBench |
| Cookie-Bench Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation | 80.4 | #6 | 1,000 web development queries (React setting) | Interactive web apps and static pages across three tiers | Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation |
| BlenderWorld (text-only) BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References (text-only subset) | 69.7 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Gray Swan IPI (15 attempts) Gray Swan Indirect Prompt Injection, attack success at 15 attempts | 31.5 | #3 | Indirect prompt-injection attacks | Adversarial prompt injection | Gemini 4 Argon evaluation methodology |
A second, independent score source. Epoch’s own figures in Epoch’s units, one line per model version Epoch evaluated (effort setting as Epoch labels it). They are not part of this site’s capability scores or rank.
| Benchmark | Variant | Score | Epoch date | Evidence |
|---|---|---|---|---|
| GPQA Diamond Accuracy on graduate-level science multiple-choice questions (best score across scorers). Unit: fraction (0–1); higher is better. | max | 0.9091 ± 0.0159 | 2026-08-24 | |
| FrontierMath Tiers 1-3 (v2) Share of private research-level math problems solved, tiers 1-3. Unit: fraction (0–1); higher is better. | max | 0.6877 ± 0.0275 | 2026-08-25 | |
| FrontierMath Tier 4 (v2) Share of private research-level math problems solved, tier 4. Unit: fraction (0–1); higher is better. | max | 0.2927 ± 0.0719 | 2026-08-25 | |
| SimpleQA Verified Short factual questions answered correctly. Unit: fraction (0–1); higher is better. | max | 0.41 ± 0.0156 | 2026-08-28 |
Source: Epoch AI, CC BY 4.0 (licence), benchmark data read once a day.
| #1 |
| 153 app-development and bug-fix tasks |
| End-to-end OpenHarmony application development |
| OpenHarmony Bench: Evaluating LLMs and Coding Agents on OpenHarmony App Development |
| ProgramBench ProgramBench: Can Language Models Rebuild Programs From Scratch? | 19.0 | #19 | 200 program reconstruction tasks | Full-repository software architecture | ProgramBench: Can Language Models Rebuild Programs From Scratch? |
| PostTrainBench (lab runs) PostTrainBench lab-run results with no stated version | 39.8 | #1 | Post-training base models under the PostTrainBench budget | Autonomous ML engineering | PostTrainBench |
| FrontierSWE FrontierSWE | 78.1 | #2 | 17 ultra-long-horizon engineering and research tasks | Ultra-long-horizon frontier software engineering | FrontierSWE: Benchmarking coding agents at the limits of human abilities |
| FrontierSWE v2 FrontierSWE v2 | 30.2 | #13 | 34 ultra-long-horizon engineering and research tasks | Ultra-long-horizon frontier software engineering | FrontierSWE v2 |
| Bug Hunt Bench Bug Hunt Bench | 19.0 | #25 | 105 planted bugs across two production TypeScript repositories | Blind production-repository bug finding and repair | Bug Hunt Bench method, caveats, and definitions |
| NL2Repo NL2Repo | 58 | #9 | Natural language to repository tasks | System-level software comprehension | MiniMax M2.7: Early Echoes of Self-Evolution |
| AA Coding Index Artificial Analysis Coding Index | 74.8 | #13 | Cross-benchmark coding index | Display-only external reference | Artificial Analysis model leaderboards |
| AA-SciCode Artificial Analysis SciCode | 59.0 | #12 | Scientific coding subproblems | Scientific programming | Artificial Analysis SciCode Benchmark Leaderboard |
| LiveCodeBench (Vals) LiveCodeBench, Vals AI run | 80.5 | #64 | Competitive programming problems (easy, medium, hard) | Frontier coding | Vals AI LiveCodeBench, Vals AI run leaderboard |
| SWE-bench (Vals) SWE-bench, Vals AI run | 95.4 | #6 | Real repository issues by human time bucket | Frontier coding agents | Vals AI SWE-bench, Vals AI run leaderboard |
| DeepSWE DeepSWE | 66.9 | #35 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | DeepSWE benchmark blog |
| OpenHarmony Bench v1.2 OpenHarmony Bench v1.2 | 60.65 | #3 | App-development, bug-fix and migration tasks (count not published) | End-to-end OpenHarmony application development and migration | OpenHarmony Bench: Evaluating LLMs and Coding Agents on OpenHarmony App Development |
| PostTrainBench PostTrainBench v1.2 | 34.5 | #10 | Post-training four base models on six benchmarks | Autonomous ML engineering | PostTrainBench |
| #32 |
| Research-level physics questions |
| Research-level physics reasoning |
| CritPt Benchmark Leaderboard |
| #26 |
| Enterprise operations workflows |
| Enterprise agent operations |
| Artificial Analysis EnterpriseOps-Gym Benchmark Leaderboard |
| AA ITBench Artificial Analysis ITBench-AA | 46.1 | #13 | IT incident-response tasks | Enterprise IT operations | Artificial Analysis ITBench-AA Benchmark Leaderboard |
| AA Tau3 Banking Artificial Analysis Tau3-Banking | 50.3 | #3 | Banking tool-use workflows | Agentic banking workflows | Artificial Analysis Tau3-Banking Benchmark Leaderboard |
| Terminal-Bench 2.1 Terminal-Bench 2.1 | 88.2 | #10 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| HLE w/ tools Humanity's Last Exam with tools | 62.5 | #7 | Expert questions with tool use | Frontier tool-augmented reasoning | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA | 1769 | #10 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA normalized | 57.5 | #12 | Economically valuable tasks | Professional agentic workflows | Artificial Analysis model benchmarks |
| AA Agentic Index Artificial Analysis Agentic Index | 53.4 | #4 | Cross-benchmark agentic index | Display-only external reference | Artificial Analysis model leaderboards |
| AA Terminal-Bench 4.0 Artificial Analysis Terminal-Bench v4.0 | 41.9 | #21 | Terminal-based agent tasks | Agentic software engineering | Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard |
| GDP.pdf Artificial Analysis GDP.pdf | 11.2 | #44 | Professional document-production tasks | Professional knowledge work | GDP.pdf Benchmark Leaderboard |
| AA-AnalystAgent Artificial Analysis AnalystAgent | 38.8 | #27 | Spreadsheet and document analysis questions | Business and data analysis | AA-AnalystAgent Benchmark Leaderboard |
| CyberGym CyberGym | 84.5 | #9 | 1,507 vulnerability analysis instances | Real-world cybersecurity | CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale |
| ExploitGym ExploitGym | 15.0 | #17 | 898 exploitation tasks | Advanced cybersecurity exploitation | ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks? |
| Toolathlon-Verified Toolathlon-Verified | 73.0 | #15 | Verified multi-tool workflows | Advanced tool use | Kimi K3: Open Frontier Intelligence |
| AutomationBench AutomationBench | 48.2 | #17 | 600 public automation tasks | Long-horizon automation | Kimi K3: Open Frontier Intelligence |
| Agents' Last Exam Agents' Last Exam | 28.5 | #15 | Agent tasks | Advanced agentic work | DeepSeek V4 Flash 0731 update |
| Terminal-Bench 2.1 (Vals) Terminal-Bench 2.1, Vals AI run | 71.5 | #25 | Difficult terminal tasks | Frontier agentic | Vals AI Terminal-Bench 2.1, Vals AI run leaderboard |
| Hermes Index Hermes Index: agentic capability and cost per task inside Hermes Agent | 39.2 | #8 | Four suites: Hermes Bench (150 tasks), TerminalBench 4 without its 4 GPU tasks, TerminalBench Science and SkillsBench | Frontier agentic | Hermes Index: an agentic model leaderboard |
| Hermes Bench Hermes Bench: 150 agent tasks graded on the files and state the agent leaves behind | 71.8 | #7 | 150 tasks across 25 categories | Frontier agentic | Hermes Bench (Hermes Index) |
| MazeBench MazeBench: visual spatial reasoning in a 3D open world | 0 | #28 | 100 hidden gems across 256 rooms in one open world | Long-horizon spatial planning, with single puzzles that can take over one hundred moves | MazeBench Results |
| CWE-bench CWE-bench v2 | 42.0 | #14 | Audit and patch C/C++, Go, Java, TypeScript/JavaScript, Python, and Rust repositories; 100 public and 150 held-out tasks | Frontier agent evaluation | CWE-bench v2 leaderboard and methodology |
| Terminal-Bench 4.1 Terminal-Bench 4.1 | 41.20 | #18 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.1 |
| AA Cyber Index Artificial Analysis Cyber Index | 36.4 | #13 | Three defensive cybersecurity evaluations | Real-world vulnerability discovery and patching | Artificial Analysis Cyber Index |
| CWE-Bench-AA Artificial Analysis CWE-Bench-AA | 55.8 | #12 | Real-world vulnerability patching tasks | Automated vulnerability remediation | CWE-Bench-AA Benchmark Leaderboard |
| DeepsecBench-AA Artificial Analysis DeepsecBench-AA | 24.3 | #12 | Vulnerability discovery in real codebases | Security code review | DeepsecBench-AA Benchmark Leaderboard |
| CyberGym-E2E-AA Artificial Analysis CyberGym-E2E-AA | 29.0 | #10 | 131 end-to-end vulnerability reproduction and patching tasks | Real-world cybersecurity | CyberGym-E2E-AA Benchmark Leaderboard |
| Finch Finch (FinWorkBench): Finance & Accounting across Spreadsheet-Centric Enterprise Workflows | 65.1 | #5 | Spreadsheet-centric finance and accounting workflows | Enterprise finance work | Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows |
| b3 Agent Security b3: Backbone Breaker Benchmark | 93.0 | #2 | Threat snapshots of attacks on agent backends | Agent security | The Backbone Breaker Benchmark |
| Cyber Misuse Refusal Refusal of harmful cyber requests (JailbreakBench, StrongREJECT, AgentHarm) | 87.0 | #3 | Cyber-related harmful prompts from three safety benchmarks | Cyber misuse safety | Mistral Large 4 is now open weight |
| #7 |
| 78 text-brief 3D creation tasks in Blender |
| Long-horizon 3D modeling and scene building |
| BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References |
| MaxxBench MaxxBench (mutated DeepSWE tasks) | 56.7 | #7 | 89 mutated DeepSWE feature-implementation tasks, two attempts per model | Long-horizon software engineering under changed requirements | Why MaxxBench (unLAP research post) |
| Chess Puzzles Chess Puzzles (Epoch AI) | 37.0 | #39 | 100 programmatically generated chess positions with a single best move | Novel chess positions, single best move | Chess Puzzles (Epoch AI) |
| Mystery Game Puzzles Mystery Game Puzzles (Epoch AI) | 33.0 | #31 | 100 single-best-move positions from an undisclosed game | Unfamiliar game positions, single best move | Mystery Game Puzzles (Epoch AI) |
| Code2Video Code2Video | 1496 | #10 | Creative briefs rendered as motion-graphics video | Code-driven motion design | BenchLM |
| Landing Page Arena Landing Page Arena | 1502 | #7 | 12 client briefs for small-business landing pages, rated by human votes | Marketing page design and copy | BenchLM |
| Joke Arena Joke Arena | 1539 | #4 | 100 joke prompts in 10 categories, rated by human votes | Humour writing | BenchLM |
| Pelican Arena Pelican Arena | 1572 | #12 | One prompt: an animated SVG of a pelican riding a bicycle, rated by human votes | Vector drawing and animation in code | BenchLM |
| Landmark Arena Landmark Arena | 1481 | #8 | 20 famous landmarks built as three.js web pages, rated by human votes | 3D scenes in browser code | BenchLM |
| BabaIsBench BabaIsBench (Baba Is You intro levels, pass@1) | 96 | #9 | 8 intro levels of Baba Is You, three attempts per level (Stage 0); 15 further levels run once (Stage 1) | Rule-rewriting puzzles that need planning over many moves | Baba Is Solved by Fable 5 and GPT-5.6 Sol, but at what cost? (Quesma) |
| NYT Connections NYT Connections LLM Benchmark (extended version) | 74.2 | #51 | 940 NYT Connections puzzles, each with up to four added trick words | Wordplay, word knowledge and decoys that fit almost-but-not-quite | NYT Connections LLM Benchmark (Lech Mazur, GitHub) |
| StealthMark StealthMark Intelligence Benchmarks (overall score) | 52.9 | #13 | 8 original tasks: Newton's Mirror, Ground Truth, Latch, Foresight, Mona Lisa, Selfie, Beach and Raccoon | Chained physical reasoning, planning without tools and precise visual construction | StealthMark: The AI Benchmark Explained (Stealth Models) |
| FrontierPhysics End-to-End Physics Research Benchmark for AI Agents | 4.2 | #11 | 56 research projects from 42 physicists across nine fields, three trials each (168 rollouts per setup) | Open-ended research projects that took their authors about 270 days on average | FrontierPhysics: Evaluating Agents for End-to-End Physics Research (arXiv, November 4, 2026) |
| HoneyBench HoneyBench v0.2 (Goodhart Labs) | 76.8 | #8 | 20 private honeypot tasks across 7 domains with exploitable evaluators | Agentic alignment and specification gaming | HoneyBench v0.2 |