Models / Qwen3.8-2.4T-A95B

Alibaba

Qwen3.8-2.4T-A95B

Early evidence, 11 results from 1 source, on 2 use cases. Qwen3.8-2.4T-A95B is best for reasoning and knowledge, and agents and tool use; pick it when quality matters more than cost. The cheapest model of similar intelligence is MiMo-V2.6-Flash, at $0.18 per million tokens against $3.00.

Results 19 Nov 2026 · 11 results · 1 source

Test Qwen3.8-2.4T-A95B on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$2.00 in · $6.00 out
Alibaba's list price, 10 Nov 2026 · compare prices
Speed
36 tokens a second; on its test prompt the answer starts after 58.0 s, thinking time included
Artificial Analysis, on its usual API
Intelligence Index
39.9
Artificial Analysis
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Alibaba, based in China
Weights published
Released
12 Aug 2026 (Artificial Analysis)
1,048,576 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 27th of 185Claude Opus 5.5 – $3.00 blended, 72nd percentilecheapest: Mistral Nemo 65th of 65Nemotron 3.5 Super VL
Models priced $3–10 per million tokens 14th of 38Claude Opus 5.5 – sets this group 15th of 15Mistral Medium 3.5
Models with similar intelligence sets this group – $3.00 blended, 52nd percentilecheapest: MiMo-V2.6-Flash 13th of 13DeepSeek-V4.1-Flash
Models writing under 50 tokens a second 4th of 9MiMo-V2.6-Pro – $3.00 blended, 75th percentilecheapest: Phi-4 sets this group
Models from developers based in China 8th of 75MiMo-V2.6-Pro – $3.00 blended, 97th percentilecheapest: Qwen3.5-9B 23rd of 23DeepSeek-V4.1-Flash
Open-weights models 7th of 104MiMo-V2.6-Pro – $3.00 blended, 96th percentilecheapest: Mistral Nemo 43rd of 43Nemotron 3.5 Super VL

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, then those priced $3–10 per million tokens. 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 29th of 159 available · 14th of 35 at its price
BenchmarkQwen3.8-2.4T-A95BRank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 11.1% 40th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 82.0% 18th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 49.1% 4th of 104 Grok 4.6 50.7%
  • 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 28th of 187 available · 16th of 39 at its price
BenchmarkQwen3.8-2.4T-A95BRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 39.9 27th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 42.4% 36th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 93.5% 10th of 168 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 Not measured
  • Vectara Hallucination Leaderboard: has not measured this model.
  • Arena (formerly LMArena): has not measured this model.
  • SimpleQA Verified (Epoch AI): 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

  • Cheaper at similar intelligenceMiMo-V2.6-Flash$0.18 blended · Intelligence Index 37.9

Against Qwen3.8-2.4T-A95B at $3.00 blended, Intelligence Index 39.9. "Similar intelligence" means within 4 points or better.

Where to run it

4 hosts on OpenRouter at the standard service tier, with a median of $3.00 blended per million tokens; quantisation where the host states it: FP8. Cheapest first.

HostQuantisationInputOutputBlended
Alibabanot stated$2.00$6.00$3.00
Novitanot stated$2.00$6.00$3.00
SiliconFlowFP8$2.00$6.00$3.00
Venicenot stated$2.00$6.00$3.00

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

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

Scroll sideways to see every alternative.

Qwen3.8-2.4T-A95BClaude Opus 5.5
most intelligent at $3–10 per million tokens
MiMo-V2.6-Flash
cheapest with similar intelligence
DeepSeek-V4.1-Flash
fastest with similar intelligence
MiMo-V2.6-Pro
most intelligent from China
Price per million tokens $3.00 $8.00$0.18$0.52$0.54
Tokens a second 36 964636943
Intelligence Index 39.9 57.637.939.546.3
Spring Prompt overall – 80–49–
Rank among available models, by use case
Product listings – 16th–18th–
Decks from an analysis – 8th–––
User surveys – 5th–––
Marketing planning – 11th–––
Agents and tool use 29th of 159 3rd42nd31st23rd
Professional work – 3rd–––
Reasoning and knowledge 28th of 187 1st55th42nd13th
Writing – 5th56th29th23rd
Sticking to the facts – 3rd46th23rd10th
Speed under pressure – ––––

Shaded figures are better than Qwen3.8-2.4T-A95B's. A dash means no result.

Where it has been measured

14th most intelligent of the 38 models priced $3–10 per million tokens. Among models available today, in the top quarter (by percentile) for reasoning and knowledge, and agents and tool use.

Every result

11 published results from 1 source, each in the source's own units, with the configuration that produced it.

Artificial Analysis · reported by Artificial Analysis · 11 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 71.9 40 of 187 Qwen3.8-2.4T-A95B 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 39.9 60 of 413 Qwen3.8-2.4T-A95B 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 93.5% 14 of 360 Qwen3.8-2.4T-A95B 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 42.4% 69 of 419 Qwen3.8-2.4T-A95B 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 80.3% 70 of 407 Qwen3.8-2.4T-A95B 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 35.7 132 of 137 Qwen3.8-2.4T-A95B 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 54.1% 68 of 205 Qwen3.8-2.4T-A95B 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 82.0% 39 of 188 Qwen3.8-2.4T-A95B 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 11.1% 94 of 204 Qwen3.8-2.4T-A95B 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 58.0 123 of 137 Qwen3.8-2.4T-A95B 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 49.1% 5 of 175 Qwen3.8-2.4T-A95B 20 Oct 2026

Not shown: Not your codebase or tools.

Will Qwen3.8-2.4T-A95B work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.