Models / Qwen3.8-Max

Alibaba

Qwen3.8-Max

Early evidence, 10 results from 2 sources, on 3 use cases. Qwen3.8-Max is best for reasoning and knowledge, and agents and tool use; it is not on sale through OpenRouter, so it is here for reference.

Superseded. Qwen4-Max is Alibaba's newer model in this line, at $2.25 blended: see Qwen4-Max.

Results 19 Nov 2026 · 10 results · 2 sources

Price per million tokens
Not available through OpenRouter
Speed
Not measured
Intelligence Index
40.2
Artificial Analysis, at 0803
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Alibaba, based in China
Weights not published
Released
3 Aug 2026 (Artificial Analysis)

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 27th of 186Claude Opus 5.5 – – –
Models from developers based in China 8th of 76MiMo-V2.6-Pro – – –

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 22nd of 160 available
BenchmarkQwen3.8-MaxRank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 18.7% 30th of 108 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 81.3% 20th of 108 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 51.3% 1st of 105 This model
  • tau2-bench: pending. Its latest results are dated 26 May 2026, before this model was released.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: pending. Its latest results are dated 30 Jun 2026, before this model was released.
  • Microsoft STATE-Bench: pending. Its latest results are dated 29 May 2026, before this model was released.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 29th of 188 available
BenchmarkQwen3.8-MaxRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 40.2 27th of 186 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 43.0% 32nd of 187 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 92.7% 18th of 169 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality Not measured
  • Arena (formerly LMArena): has not measured this model.
  • UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers 61st of 140 available
BenchmarkQwen3.8-MaxRank among availableBest available
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 45.8% 33rd of 69 GPT-6 Astra 75.6%
  • Vectara Hallucination Leaderboard: has not measured this model.
  • Arena (formerly LMArena): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

  • Alibaba's newer model in this lineQwen4-Max$2.25 blended
  • Open weights at similar intelligenceMiMo-V2.6-Flash$0.18 blended · Intelligence Index 37.9

Against Qwen3.8-Max, Intelligence Index 40.2. "Similar intelligence" means within 4 points or better.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

Qwen3.8-MaxClaude Opus 5.5
most intelligent available today
MiMo-V2.6-Pro
most intelligent from China
Claude Fable 5.2
leads overall
Qwen4-Max
Alibaba's best other model
Price per million tokens – $8.00$0.54$16.00$2.25
Tokens a second – 9643––
Intelligence Index 40.2 57.646.3––
Spring Prompt overall – 80–8853
Rank among available models, by use case
Product listings – 16th–8th22nd
Decks from an analysis – 8th–4th1st
User surveys – 5th–1st6th
Marketing planning – 11th–1st18th
Agents and tool use 22nd of 160 3rd22nd––
Professional work – 3rd–––
Reasoning and knowledge 29th of 188 1st13th––
Writing – 5th23rd––
Sticking to the facts 61st of 140 3rd10th––
Speed under pressure – ––10th29th

Shaded figures are better than Qwen3.8-Max's. A dash means no result.

Where it has been measured

Compared with the models available today (it is not on sale itself), in the top quarter (by percentile) for reasoning and knowledge, and agents and tool use.

Artificial Analysis lists it but has not published a speed for it yet

Every result

10 published results from 2 sources, each in the source's own units, with the configuration that produced it.

Artificial Analysis · reported by Artificial Analysis · 9 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 71.8 41 of 187 Qwen3.8-Max (0803) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 40.2 59 of 413 Qwen3.8-Max (0803) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 92.7% 32 of 360 Qwen3.8-Max (0803) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 43.0% 62 of 419 Qwen3.8-Max (0803) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 78.3% 109 of 407 Qwen3.8-Max (0803) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 53.2% 78 of 205 Qwen3.8-Max (0803) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 81.3% 41 of 188 Qwen3.8-Max (0803) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 18.7% 71 of 204 Qwen3.8-Max (0803) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 51.3% 1 of 175 Qwen3.8-Max (0803) 20 Oct 2026

Not shown: Not your codebase or tools.

SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
MeasureValueRankConfigurationDated
SimpleQA Verified: correct answers% of questions, higher is better 45.8% 36 of 85 Qwen3.8-Max (0803, xhigh reasoning) 27 Aug 2026

Not shown: Not answers grounded in your documents; tests what the model remembers.

Test your own prompt.

Benchmarks aren't your task. Run your prompt on the models you could use, with every answer checked and costed.