Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | — | 320B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 1M | 1M |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $0.0399Relace |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.0784Relace |
| — | $11.90Relace · fp4 | |
| Benchmarks | ||
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | 75.7% | 63.4% |
Terminal-Bench 4.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better. | 48.5% | 35.76% |
CursorBench 4.0Agentic coding — Cursor's own test of coding agents on ambiguous, multi-file tasks taken from real Cursor sessions — editing, refactoring, investigating a codebase, understanding what the user meant, managing jobs and following a design. Cursor runs each model at several reasoning efforts; each release here carries the score of its best listed effort. Scores aren't comparable with earlier CursorBench versions. Higher is better. | — | 36.8% |
NL2Repo-BenchRepo-level code generation — Tests whether the AI can turn a natural-language requirement into working code across an entire repository, not just produce a single function or patch. Higher is better. | — | 56.3% |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 84.3% |
APEX-AgentsExpert agentic work — expert-level agentic work tasks (AI Productivity Index) | 72.1% | — |
JobBenchProfessional tool use — Tests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | 68.5% | — |
Toolathlon-VerifiedPersonal tool use — Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. | — | 78.4% |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | 51.7% | — |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 55.3% |
BioMysteryBench · human solvedBiology — Real biology puzzles that human experts have managed to crack — can the AI reach the same answers? Higher is better. | 85% | — |
Agents’ Last Exam v1.1Agentic computer use — averaged rubric score on the 122-task October 17, 2026 v1.1 set, using ALE-Claw with a five-hour limit; separate from earlier ALE scores | 46.7% | — |
Agent's Last Exam · pass@1Agentic computer use — A hard set of desktop and operating-system tasks an AI agent has to finish by looking at the screen and working the machine itself. The score is the share it passes outright — partial credit does not count. Higher is better. | — | 26.3% |
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. | — | 48.8% |
AutomationBench (Artificial Analysis)Business workflows — The same business-workflow test, run by Artificial Analysis rather than by the lab, and graded strict pass@1: a workflow counts only if the whole of it is right on the first attempt. Read it as a separate board from the lab-run AutomationBench scores. Higher is better. | 72.5% | — |
HealthBench ProfessionalHealth — Realistic health conversations graded against detailed rubrics written by physicians — can the AI respond the way a careful medical professional would? Higher is better. | 60% | — |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | — | 1773 |
AA-Briefcase v1.1Knowledge work — Artificial Analysis agentic office-work eval (Elo, v1.1 rating fit) | 1686 | — |
CharXiv Reasoning · with toolsChart reasoning — The same chart-and-figure reasoning test, run with the AI allowed to use tools — writing code to inspect the image, for instance — rather than reading the chart unaided. Scores run higher than the unaided version, so read the two as separate tests. Higher is better. | — | 89.4% |
Chartography · with toolsChart tasks — A chart-centred test run with tools available to the AI, reported separately from the chart-reading benchmarks above it. Higher is better. | — | 78% |
Chartography · no toolsChart tasks — The same chart-centred test with no tools: the AI has to read each chart unaided. Scores run far lower than the with-tools version, so read the two as separate tests. Higher is better. | 54.2% | — |
OfficeQA ProDocument Q&A — Questions about office documents, where answering depends on reading the page as a document — layout, tables and figures included — rather than as loose text. Higher is better. | — | 62.4% |
MVBenchVideo understanding — Video questions that cannot be answered from any single frame: the AI has to follow what changes over time — the order things happen in, what moved where. Higher is better. | — | 77.8% |
MMVUVideo reasoning — Expert-level video questions drawn from specific disciplines, where answering means applying subject knowledge to what is happening on screen rather than just describing it. Higher is better. | — | 80.5% |
BabyVisionVisual reasoning — Tests core visual reasoning — seeing and understanding images the way even young children can, which AIs often find surprisingly hard. Higher is better. | — | 53.4% |
threejsevalCommunity preference (Three.js) — Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better. | — | 1373 |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Nov 11 2026 | Aug 26 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Qwen4-MaxvsClaude Fable 5.2GLM-5.3-FlashvsClaude Fable 5.2Qwen4-MaxvsGPT-6.1 TerraGLM-5.3-FlashvsGPT-6.1 TerraQwen4-MaxvsGemini 4 HydrogenGLM-5.3-FlashvsGemini 4 HydrogenQwen4-MaxvsMuse EmberGLM-5.3-FlashvsMuse EmberQwen4-MaxvsGrok 4.7GLM-5.3-FlashvsGrok 4.7Qwen4-MaxvsDeepSeek-V4.1-Flash-1017GLM-5.3-FlashvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen4-Max leads GLM-5.3-Flash on 2 of the 2 benchmarks they both report (DeepSWE 1.1, Terminal-Bench 4.0). GLM-5.3-Flash shipped 77 days before Qwen4-Max, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Qwen4-Max) vs 1M (GLM-5.3-Flash). Qwen4-Max is closed, while GLM-5.3-Flash is open weight.
On DeepSWE 1.1, Qwen4-Max leads at 75.7% vs GLM-5.3-Flash at 63.4%. On Terminal-Bench 4.0, Qwen4-Max leads at 48.5% vs GLM-5.3-Flash at 35.76%.