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.
Alibaba · Open Weight · rank 35 · bench-align-v5
Qwen3.8 Max is built for coding, agent work and reasoning. It ranks in the top quarter for instruction following (top 2% of 159 scored models) and multimodal tasks (top 3% of 136 scored models), by BenchLM's published scores.
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.
Qwen3.8 Max by Alibaba scores 65.5 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 | 52.16 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 41 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 |
|---|---|---|---|---|---|
| GPQA Graduate-Level Google-Proof Q&A | 92.6 | #18 | 448 questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| GPQA-D GPQA Diamond | 92.6 | #20 | Graduate-level science questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| HLE Humanity's Last Exam | 43.6 | #33 | Expert-level questions | Frontier expert level | Humanity's Last Exam |
| HLE w/o tools Humanity's Last Exam without tools | 43.6 | #21 | Expert-level questions | Frontier expert level | Introducing GPT-5.4 mini and nano |
| GPQA Diamond (Vals) GPQA Diamond, Vals AI run | 93.7 | #6 | Graduate-level science questions | Expert reasoning | Vals AI GPQA Diamond, Vals AI run leaderboard |
| MMLU-Pro (Vals) MMLU-Pro, Vals AI run | 88.6 | #18 | 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 | 86.6 | #15 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| SWE-bench Pro SWE-bench Pro | 67.7 | #11 | 1,865 repository problems | Long-horizon professional engineering | SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks? |
| VulcanBench v3 VulcanBench v3 | 81.2 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3) FrontierMath v2 Tiers 1-3 | 74.737 | #26 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | FrontierMath v2 benchmark hub |
| FrontierMath v2 (Tier 4) FrontierMath v2 Tier 4 | 46.341 | #25 | 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 |
|---|---|---|---|---|---|
| LongBench v2 LongBench v2 | 66.3 | #6 | Long-context tasks | Hard long-context | LongBench v2 |
| MRCRv2 MRCRv2 | 92.9 | #2 | Long-context retrieval | Hard long-context | Introducing GPT-5.2 and GPT-5.2 Pro |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 Terminal-Bench 2.1 | 86.6 | #16 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| HLE w/ tools Humanity's Last Exam with tools | 56.2 | #16 | Expert questions with tool use | Frontier tool-augmented reasoning | DeepSeek-V4 Technical Report |
| OSWorld-Verified OSWorld-Verified | 86.1 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| MMMU-Pro Massive Multi-discipline Multimodal Understanding Pro | 82.3 | #6 | Multimodal academic reasoning | Frontier multimodal | MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark |
| OCRBench V2 OCRBench V2 | 74.2 | #1 | Image OCR tasks | Native visual text understanding | OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning |
| MathVision w/ Python MathVision with Python | 97.7 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Chess Puzzles Chess Puzzles (Epoch AI) | 46.0 | #26 | 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) | 38.0 | #23 | 100 single-best-move positions from an undisclosed game | Unfamiliar game positions, single best move | Mystery Game Puzzles (Epoch AI) |
| MirrorCode MirrorCode (Epoch AI and METR) | 52.2 |
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. | xhigh | 0.9268 ± 0.0169 | 2026-08-04 | |
| FrontierMath Tiers 1-3 (v2) Share of private research-level math problems solved, tiers 1-3. Unit: fraction (0–1); higher is better. | xhigh | 0.7474 ± 0.0258 | 2026-08-04 | |
| FrontierMath Tier 4 (v2) Share of private research-level math problems solved, tier 4. Unit: fraction (0–1); higher is better. | xhigh | 0.4634 ± 0.0788 | 2026-08-04 | |
| SimpleQA Verified Short factual questions answered correctly. Unit: fraction (0–1); higher is better. | xhigh | 0.458 ± 0.0158 | 2026-08-27 |
Source: Epoch AI, CC BY 4.0 (licence), benchmark data read once a day.
People's votes between two anonymous answers on arena.ai, one board per task. LMArena's own ratings and ranks, one line per model version it rates; not part of this site's capability scores or rank.
| Board | Variant | Rating | Votes | Rank | Published | Evidence |
|---|---|---|---|---|---|---|
| Vision Arena People's votes between two answers about the same image, style-controlled. | — | 1,294 ± 7 | 10,833 | 8 | 2026-11-19 |
Source: LMArena, CC BY 4.0 (licence), leaderboard data read once a day.
| #11 |
| 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 | #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 |
| FrontierSWE FrontierSWE | 73.5 | #3 | 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 | 15.8 | #23 | 34 ultra-long-horizon engineering and research tasks | Ultra-long-horizon frontier software engineering | FrontierSWE v2 |
| Bug Hunt Bench Bug Hunt Bench | 25.7 | #22 | 105 planted bugs across two production TypeScript repositories | Blind production-repository bug finding and repair | Bug Hunt Bench method, caveats, and definitions |
| MLS-Bench Lite MLS-Bench Lite | 41.0 | #2 | 30 machine-learning research tasks | ML research and systems engineering | MLS-Bench |
| PaperBench PaperBench | 93.0 | #1 | AI research-paper reproduction | Frontier autonomous research and engineering | Qwen3.8-Max: A New Bar for Coding and Cowork |
| QwenReactBench QwenReactBench | 1724 | #1 | Bilingual React project construction | Production frontend development | Qwen3.8-Max: A New Bar for Coding and Cowork |
| NL2Repo NL2Repo | 55.9 | #11 | Natural language to repository tasks | System-level software comprehension | MiniMax M2.7: Early Echoes of Self-Evolution |
| LiveCodeBench (Vals) LiveCodeBench, Vals AI run | 87.9 | #10 | Competitive programming problems (easy, medium, hard) | Frontier coding | Vals AI LiveCodeBench, Vals AI run leaderboard |
| SWE-bench (Vals) SWE-bench, Vals AI run | 85.6 | #17 | Real repository issues by human time bucket | Frontier coding agents | Vals AI SWE-bench, Vals AI run leaderboard |
| DeepSWE DeepSWE | 56.6 | #53 | 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 | 67.77 | #2 | 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 |
| ScarfBench ScarfBench: Cross-Framework Application Migration in Enterprise Java | 63.7 | #8 | 204 framework migration tasks across 34 enterprise Java applications | Whole-application framework migration | ScarfBench: A Benchmark for Cross-Framework Application Migration in Enterprise Java |
| #1 |
| 369 real-world computer tasks (361 when eight Google Drive tasks are excluded) |
| Multi-step desktop and cross-application workflows |
| OSWorld |
| OSWorld 2.0 OSWorld 2.0 | 19.4 | #16 | 108 long-horizon computer-use workflows | Long-horizon professional workflows | OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks |
| JobBench JobBench | 53.4 | #14 | 130 tasks across 35 occupations | Professional multi-source workflows | JobBench: Aligning Agent Work With Human Will |
| AndroidWorld AndroidWorld | 85.3 | #2 | Android app workflows | Complex mobile task completion | GLM-5V-Turbo |
| Toolathlon-Verified Toolathlon-Verified | 72.5 | #17 | Verified multi-tool workflows | Advanced tool use | Kimi K3: Open Frontier Intelligence |
| AutomationBench AutomationBench | 27.3 | #32 | 600 public automation tasks | Long-horizon automation | Kimi K3: Open Frontier Intelligence |
| Agents' Last Exam Agents' Last Exam | 52.4 | #4 | Agent tasks | Advanced agentic work | DeepSeek V4 Flash 0731 update |
| WideResearch WideResearch | 81.9 | #3 | Open-ended research tasks | Broad research-agent workflows | Qwen3.6 launch benchmarks |
| CoWorkBench CoWorkBench | 74.8 | #2 | Long-horizon professional workflows | Cross-domain professional work | Qwen3.8-Max: A New Bar for Coding and Cowork |
| MobileWorld MobileWorld | 77.8 | #1 | Interactive mobile-device workflows | Long-horizon mobile computer use | Qwen3.8-Max: A New Bar for Coding and Cowork |
| WebArena-Verified WebArena-Verified Browser Agent Benchmark | 66.8 | #2 | 812 verified tasks; separate 258-task Hard subset | Audited stateful browser work | WebArena-Verified: A Fully Audited Benchmark for Web Agents |
| Terminal-Bench 2.1 (Vals) Terminal-Bench 2.1, Vals AI run | 67.4 | #33 | 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 | 36.2 | #13 | 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 | 70.5 | #12 | 150 tasks across 25 categories | Frontier agentic | Hermes Bench (Hermes Index) |
| MazeBench MazeBench: visual spatial reasoning in a 3D open world | 0 | #29 | 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 | 45.4 | #18 | 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 |
| #2 |
| Visual mathematics problems with Python |
| Advanced multimodal mathematics |
| Kimi K3: Open Frontier Intelligence |
| BabyVision w/ Python BabyVision with Python | 91.3 | #5 | Visual perception tasks with Python | Fine-grained visual perception | Kimi K3: Open Frontier Intelligence |
| ZeroBench w/ Python ZeroBench_main with Python | 49.0 | #4 | Visual reasoning questions with Python | Tool-augmented visual reasoning | Kimi K3: Open Frontier Intelligence |
| PerceptionBench PerceptionBench (Internal) | 63.5 | #3 | Internal atomic visual-perception tasks | Fine-grained visual perception | Kimi K3: Open Frontier Intelligence |
| OmniDocBench 1.5 OmniDocBench 1.5 | 92.1 | #1 | Document understanding tasks | Grounded document reasoning | Introducing GPT-5.4 mini and nano |
| RealWorldQA RealWorldQA | 88.0 | #2 | Real-world visual question answering | General visual reasoning | Qwen3.6 launch benchmarks |
| Video-MME (with subtitle) Video-MME with subtitle | 90.4 | #1 | Video understanding | Multimodal video reasoning | Qwen3.6 launch benchmarks |
| MathVision MathVision | 95.2 | #1 | Visually grounded math problems | Advanced multimodal mathematics | Qwen3.6 launch benchmarks |
| CC-OCR CC-OCR | 79.6 | #6 | Optical character recognition | Document reading | Qwen3.6 launch benchmarks |
| ERQA ERQA | 77.8 | #2 | Evidence-based visual QA | Grounded multimodal reasoning | Qwen3.6 launch benchmarks |
| VideoMMMU VideoMMMU | 88.7 | #1 | Video-grounded expert reasoning | Frontier multimodal video reasoning | Qwen3.6 launch benchmarks |
| MLVU (M-Avg) MLVU mean average | 90.8 | #1 | General video understanding | Broad multimodal video reasoning | Qwen3.6 launch benchmarks |
| LVBench LVBench | 81.8 | #4 | Long-form video question answering | Extended temporal reasoning | Qwen3.8-Max: A New Bar for Coding and Cowork |
| MMVU Multimodal Multi-disciplinary Video Understanding | 82.4 | #1 | Video understanding | Multi-disciplinary multimodal video reasoning | Kimi K2.5 benchmark release surface |
| ScreenSpot Pro ScreenSpot Pro | 84.5 | #4 | 1,581 grounding instructions | Professional GUI grounding | ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use |
| MedXpertQA (MM) MedXpertQA Multimodal | 80.4 | #2 | 2,000 multimodal medical questions | Clinical multimodal reasoning | Muse Spark Eval Methodology |
| ZeroBench ZeroBench | 24.0 | #6 | 100 visual reasoning questions | Tool-augmented visual reasoning | Muse Spark Eval Methodology |
| Vision2Web Vision2Web | 69.0 | #2 | Screenshot-to-web tasks | Multimodal web generation | GLM-5V-Turbo |
| SimpleVQA SimpleVQA | 75.0 | #3 | Visual QA tasks | General visual understanding | GLM-5V-Turbo |
| CharXiv CharXiv Reasoning | 93.5 | #1 | Scientific chart reasoning | Scientific visualization reasoning | CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs |
| CharXiv w/o tools CharXiv Reasoning without tools | 88.4 | #3 | Scientific chart reasoning (tool-free) | Scientific visualization reasoning | CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs |
| BabyVision BabyVision | 82.0 | #1 | Visual perception tasks | Fine-grained visual perception | Muse Spark 1.1 Evaluation Report |
| #18 |
| 30 reimplementation tasks (15 programs in two languages), three attempts each |
| Days-long software engineering without source code |
| MirrorCode (Epoch AI) |
| Epoch Automation Reports Epoch Automation Reports | 53.0 | #4 | 11 open-ended work tasks in five categories from Epoch AI's own work | Open-ended professional research and design work | Epoch Automation Reports |
| FACTS Multimodal FACTS Multimodal | 51.5 | #8 | About 1,500 image questions: 711 public and 811 held out | Image-grounded factual answering | BenchLM |
| Code2Video Code2Video | 1533 | #9 | Creative briefs rendered as motion-graphics video | Code-driven motion design | BenchLM |
| Landing Page Arena Landing Page Arena | 1587 | #3 | 12 client briefs for small-business landing pages, rated by human votes | Marketing page design and copy | BenchLM |
| Joke Arena Joke Arena | 1456 | #22 | 100 joke prompts in 10 categories, rated by human votes | Humour writing | BenchLM |
| Pelican Arena Pelican Arena | 1583 | #10 | 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 | 1474 | #7 | 20 famous landmarks built as three.js web pages, rated by human votes | 3D scenes in browser code | BenchLM |
| ASCII Arena ASCII Arena | 1262 | #15 | ASCII drawings of subjects from Google's Quick, Draw! dataset, rated by human votes | Text-character drawing | BenchLM |
| BabaIsBench BabaIsBench (Baba Is You intro levels, pass@1) | 58 | #24 | 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) | 88.3 | #27 | 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) | 62.4 | #7 | 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) |
| HoneyBench HoneyBench v0.2 (Goodhart Labs) | 66.2 | #12 | 20 private honeypot tasks across 7 domains with exploitable evaluators | Agentic alignment and specification gaming | HoneyBench v0.2 |