Inference
EN
Alibaba

Qwen 3.6 Max (preview)

Qwen 3.6 Max (preview) is a reasoning model from Alibaba in the Qwen 3.6 Max family. 21 benchmarks count toward its index, in 6 categories.

  • Closed weights
  • Reasoning
  • Input: text
  • Released 2026-04
  • Retires 9 Oct 2026
RankedEnough results for an index.
IndexAll categories, out of 100.57.2±5.0Median 51.0
CoverageIndex weight that has results.85%
SpeedOutput tokens per second.75/sMedian 67/s
First tokenSeconds to the first output token.0.9 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$1.03Median $0.60
Output / 1MUS dollars per 1M output tokens.$6.16Median $2.55
ContextMaximum tokens in one request.262KMedian 262K
EloLMArena rating and rank.1446±8 #60Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
qwen/qwen3.6-max-preview
Max outputMaximum output tokens per request.
66K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
—
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
9 Oct 2026

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.5 counted59.277 / 218
CodingCode writing and repair.4 counted57.084 / 209
ReasoningLogic problems and puzzles.3 counted53.494 / 227
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.5 counted59.366 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted60.6—
MathMath problems.3 counted53.273 / 168

Results

21 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Artificial Analysis IFBenchInstruction76.6%11 / 146
τ²-Bench Tool-Agent-User EvaluationAgentic95.9%13 / 149
SuperGPQA: Scaling LLM Evaluation Across 285 Graduate DisciplinesKnowledge73.9%3 / 22
Artificial Analysis Long Context ReasoningReasoning80.7%37 / 217
Artificial Analysis GPQA DiamondKnowledge88.8%49 / 199
Terminal-Bench 2.0 · Vals AIAgentic51.7% ±5.318 / 66
SWE-Bench verified · Epoch AICoding76.7% ±1.99 / 32
OTIS Mock AIME 2024-2025Math91.1% ±4.358 / 200
GPQA diamond · Epoch AIKnowledge87.4% ±2.463 / 217
Terminal-Bench 2.0 · BenchLMAgentic65.4%12 / 41
SimpleQA VerifiedKnowledge52.0% ±1.627 / 91
QwenClawBenchAgentic59.0%3 / 10
Artificial Analysis Humanity's Last ExamKnowledge30.8%73 / 222
Artificial Analysis Omniscience AccuracyKnowledge37.9%60 / 164
Scientific Code BenchmarkCoding47.0%13 / 35
FrontierMath-2025-02-28-PrivateMath23.1% ±2.526 / 69
Critical Physics TasksReasoning3.7%93 / 214
FrontierMath-Tier-4-2025-07-01-PrivateMath4.2% ±2.926 / 55
SWE-bench ProCoding57.3%43 / 83
Mystery Game PuzzlesReasoning19.0% ±3.946 / 80
NL2RepoCoding42.9%22 / 36
SWE-benchCoding72.8% ±2.054 / 87
Terminal-Bench HardAgentic43.9%18 / 23
FrontierMath-Tier-4-2025-07-01-PublicMath0.0%3 / 36
CorpFin v2Finance66.5% ±0.918 / 131
FrontierMath-2025-02-28-PublicMath50.0% ±16.716 / 64
Finance Agent v1.1Finance52.8% ±2.922 / 51
CaseLaw v2Legal47.9% ±1.150 / 53

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseEpoch AICC BYVals AINo licence stated

History

5 releases
Index58.3 → 57.2
23 Oct 202612 Nov 2026
Output / 1M$6.16 → $6.16
23 Oct 202612 Nov 2026

Questions

How much does Qwen 3.6 Max (preview) cost?
$1.03 per 1M input tokens, $6.16 per 1M output tokens.
How good is Qwen 3.6 Max (preview)?
Its index is 57.2 out of 100. That is place 91 of 283 ranked models.
What is Qwen 3.6 Max (preview) best at?
Knowledge: 59.3 out of 100, place 66 of 268.
How fast is Qwen 3.6 Max (preview)?
75 output tokens per second, 0.9 s to the first token.
What is the context window of Qwen 3.6 Max (preview)?
262K tokens.
Is Qwen 3.6 Max (preview) open source?
No. Its weights are not published.
When was Qwen 3.6 Max (preview) released?
April 2026.

Badge

Qwen 3.6 Max (preview) on Inference360: place 91 of 283, index 57.2
HTML
<a href="https://inference360.ai/models/qwen3-6-max-preview"><img src="https://inference360.ai/badges/qwen3-6-max-preview.svg" alt="Qwen 3.6 Max (preview) on Inference360: place 91 of 283, index 57.2" height="20"></a>
Markdown
[![Qwen 3.6 Max (preview) on Inference360: place 91 of 283, index 57.2](https://inference360.ai/badges/qwen3-6-max-preview.svg)](https://inference360.ai/models/qwen3-6-max-preview)

Compare with

Claude Sonnet 4.657.0Gemini 3 Flash Preview57.5MiMo-V2.5-Pro56.3Qwen3.6-27B52.1Qwen3.6-35B-A3B50.6

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeGLM-5.3-Flash63.1 · $0.078/1M

More from Alibaba

All models
Qwen3.6-27B52.1Qwen3.6-35B-A3B50.6Qwen3.6 FlashUnrankedQwen3.6 Plus54.6Qwen3.7 Max60.5