Qwen3 Max
qwen/qwen3-max
Qwen3 Max is a text-only model from the Qwen provider, released on 2025-09-05. It supports a context length of 262 144 tokens, tool usage, and does not support reasoning; its weights are not open. Pricing is $0.78 per million input tokens and $3.90 per million output tokens.
- tool use
- structured outputs
At a glance
Specifications
What the API gives you
- Context window
- 262K tokens
- Max output
- 66K tokens
- Input price
- $0.78 / 1M tokens
- Output price
- $3.90 / 1M tokens
- Cache read
- $0.16 / 1M tokens
- Modalities
- text → text
- Knowledge cutoff
- Jun 30, 2025
- Released
- Jan 1, 2025
Measured evidence
Public benchmark record
- Design Arena Coding
- 1140 Elo2026-07-28
- Design Arena Coding
- 1140 Elo2026-07-27
- Design Arena Coding
- 1140 Elo2026-07-30
- Design Arena Coding
- 1140 Elo2026-07-29
- Design Arena Coding
- 1140 Elo2026-07-31
- Design Arena Coding
- 1139 Elo2026-08-02
- Design Arena Coding
- 1138 Elo2026-08-05
- Design Arena Coding
- 1139 Elo2026-08-01
- Design Arena Coding
- 1137 Elo2026-08-09
- Design Arena Coding
- 1139 Elo2026-08-03
- Design Arena Coding
- 1139 Elo2026-08-04
- Design Arena Coding
- 1134 Elo2026-08-14
- Design Arena Coding
- 1138 Elo2026-08-06
- Design Arena Coding
- 1137 Elo2026-08-10
- Design Arena Coding
- 1139 Elo2026-08-07
- Design Arena Coding
- 1129 Elo2026-08-18
- Design Arena Coding
- 1137 Elo2026-08-08
- Design Arena Coding
- 1129 Elo2026-08-15
- Design Arena Coding
- 1137 Elo2026-08-11
- Design Arena Coding
- 1136 Elo2026-08-12
- Design Arena Coding
- 1135 Elo2026-08-13
- Design Arena Coding
- 1127 Elo2026-08-19
- Design Arena Coding
- 1134 Elo2026-08-27
- Design Arena Coding
- 1127 Elo2026-08-20
- Design Arena Coding
- 1129 Elo2026-08-16
- Design Arena Coding
- 1129 Elo2026-08-17
- Design Arena Coding
- 1134 Elo2026-08-21
- Design Arena Coding
- 1134 Elo2026-08-22
- Design Arena Coding
- 1134 Elo2026-08-23
- Design Arena Coding
- 1134 Elo2026-08-28
- Design Arena Coding
- 1135 Elo2026-08-24
- Design Arena Coding
- 1135 Elo2026-08-25
- Design Arena Coding
- 1135 Elo2026-08-26
- Design Arena Coding
- 1134 Elo2026-08-29
- Design Arena Coding
- 1133 Elo2026-08-30
- Design Arena Coding
- 1133 Elo2026-08-31
- Design Arena Coding
- 1134 Elo2026-09-01
- Design Arena Coding
- 1132 Elo2026-09-02
- Design Arena Coding
- 1130 Elo2026-09-03
- Design Arena Coding
- 1129 Elo2026-09-04
- Design Arena UI
- 1114 Elo2026-07-28
- Design Arena UI
- 1114 Elo2026-07-27
- Design Arena UI
- 1114 Elo2026-07-30
- Design Arena UI
- 1114 Elo2026-07-29
- Design Arena UI
- 1113 Elo2026-07-31
- Design Arena UI
- 1114 Elo2026-08-02
- Design Arena UI
- 1114 Elo2026-08-01
- Design Arena UI
- 1113 Elo2026-08-05
- Design Arena UI
- 1111 Elo2026-08-09
- Design Arena UI
- 1114 Elo2026-08-03
- Design Arena UI
- 1114 Elo2026-08-04
- Design Arena UI
- 1109 Elo2026-08-14
- Design Arena UI
- 1113 Elo2026-08-06
- Design Arena UI
- 1113 Elo2026-08-07
- Design Arena UI
- 1111 Elo2026-08-10
- Design Arena UI
- 1111 Elo2026-08-08
- Design Arena UI
- 1103 Elo2026-08-18
- Design Arena UI
- 1111 Elo2026-08-11
- Design Arena UI
- 1104 Elo2026-08-15
- Design Arena UI
- 1111 Elo2026-08-12
- Design Arena UI
- 1111 Elo2026-08-13
- Design Arena UI
- 1103 Elo2026-08-19
- Design Arena UI
- 1104 Elo2026-08-16
- Design Arena UI
- 1103 Elo2026-08-20
- Design Arena UI
- 1104 Elo2026-08-27
- Design Arena UI
- 1103 Elo2026-08-17
- Design Arena UI
- 1105 Elo2026-08-21
- Design Arena UI
- 1105 Elo2026-08-22
- Design Arena UI
- 1105 Elo2026-08-23
- Design Arena UI
- 1105 Elo2026-08-24
- Design Arena UI
- 1104 Elo2026-08-28
- Design Arena UI
- 1106 Elo2026-08-25
- Design Arena UI
- 1106 Elo2026-08-26
- Design Arena UI
- 1105 Elo2026-08-29
- Design Arena UI
- 1105 Elo2026-08-30
- Design Arena UI
- 1105 Elo2026-08-31
- Design Arena UI
- 1104 Elo2026-09-01
- Design Arena UI
- 1104 Elo2026-09-02
- Design Arena UI
- 1102 Elo2026-09-03
- Design Arena UI
- 1100 Elo2026-09-04
- Design Arena Website
- 1144 Elo2026-07-28
- Design Arena Website
- 1143 Elo2026-07-30
- Design Arena Website
- 1144 Elo2026-07-27
- Design Arena Website
- 1144 Elo2026-07-29
- Design Arena Website
- 1143 Elo2026-07-31
- Design Arena Website
- 1142 Elo2026-08-02
- Design Arena Website
- 1142 Elo2026-08-01
- Design Arena Website
- 1142 Elo2026-08-05
- Design Arena Website
- 1143 Elo2026-08-03
- Design Arena Website
- 1141 Elo2026-08-09
- Design Arena Website
- 1142 Elo2026-08-04
- Design Arena Website
- 1138 Elo2026-08-14
- Design Arena Website
- 1142 Elo2026-08-06
- Design Arena Website
- 1142 Elo2026-08-07
- Design Arena Website
- 1141 Elo2026-08-10
- Design Arena Website
- 1141 Elo2026-08-08
- Design Arena Website
- 1130 Elo2026-08-18
- Design Arena Website
- 1141 Elo2026-08-11
- Design Arena Website
- 1130 Elo2026-08-15
- Design Arena Website
- 1140 Elo2026-08-12
- Design Arena Website
- 1139 Elo2026-08-13
- Design Arena Website
- 1130 Elo2026-08-19
- Design Arena Website
- 1130 Elo2026-08-16
- Design Arena Website
- 1130 Elo2026-08-20
- Design Arena Website
- 1138 Elo2026-08-27
- Design Arena Website
- 1130 Elo2026-08-17
- Design Arena Website
- 1139 Elo2026-08-21
- Design Arena Website
- 1139 Elo2026-08-22
- Design Arena Website
- 1139 Elo2026-08-23
- Design Arena Website
- 1139 Elo2026-08-24
- Design Arena Website
- 1139 Elo2026-08-28
- Design Arena Website
- 1139 Elo2026-08-25
- Design Arena Website
- 1139 Elo2026-08-26
- Design Arena Website
- 1138 Elo2026-08-29
- Design Arena Website
- 1138 Elo2026-08-30
- Design Arena Website
- 1138 Elo2026-08-31
- Design Arena Website
- 1138 Elo2026-09-01
- Design Arena Website
- 1137 Elo2026-09-02
- Design Arena Website
- 1135 Elo2026-09-03
- Design Arena Website
- 1134 Elo2026-09-04
LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference.
Task evidence
How broad is the support?
Each status is exact to this model version and the selected task. Official release claims remain provisional.
- Best LLM for Frontend & UIProvisional evidence
60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for CodingProvisional evidence
24% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 8 of 8 configured evaluation feeds currently have results.
- Best Cheap LLM for High VolumeProvisional evidence
17% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.
- Cheapest Capable LLMProvisional evidence
17% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Fast SummariesProvisional evidence
14% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.
- Best Value LLMProvisional evidence
14% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for High-Volume ExtractionProvisional evidence
13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Route reliability. 2 of 4 configured evaluation feeds currently have results.
- Best LLM for Code CompletionProvisional evidence
13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for Literary TranslationProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Everyday TranslationProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for TranslationProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Debugging & Code ReviewProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 6 of 6 configured evaluation feeds currently have results.
- Best LLM for Document SummarizationProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.
- Best LLM for Tool & Function CallingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Business WritingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Creative Writing. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Logic & Problem SolvingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Marketing CopyProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Creative Writing. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for SummarizationProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.
- Best LLM for Chat & RoleplayProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Creative WritingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Computer & Browser UseProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for OCR & DocumentsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Image UnderstandingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Reasoning or LMArena Vision. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Vision & DocumentsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for WritingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Grounded RAGProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.
- Best LLM for Roleplay & CharacterProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Charts & DiagramsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Document ParsingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for a General AssistantProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
- Best Open-Weight LLM for Self-HostingProvisional evidence
8% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Massive ContextProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Long Query. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Hermes AgentProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for OpenHandsProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for GooseProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for RAG & Long ContextProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.
- Best LLM for OpenClawProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for JSON & Schema OutputProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Structured Data ExtractionProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 configured evaluation feeds currently have results.
- Best Local LLM for CodingProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Competition MathProvisional evidence
5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Agentic CodingProvisional evidence
5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Design Arena Full-stack or Design Arena Web-apps. 8 of 8 configured evaluation feeds currently have results.
- Best LLM for Autonomous AgentsProvisional evidence
5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Frontier-Bench or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.
- Best LLM for Math & ReasoningProvisional evidence
5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for AI AgentsProvisional evidence
5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.
Recommendation coverage
Where this model appears
Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.
Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.