Models / Qwen3-235B-A22B-Thinking-2507

Alibaba

Qwen3-235B-A22B-Thinking-2507

Qwen3-235B-A22B-Thinking-2507 trails most of the field on what it has been measured on; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is gpt-oss-20b, at $0.06 per million tokens against $1.21.

Results 16 Nov 2026 · 23 results · 5 sources

Test Qwen3-235B-A22B-Thinking-2507 on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.45 in · $3.50 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
12.7
Artificial Analysis
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Alibaba, based in China
Weights published
Released
25 Jul 2025 (Artificial Analysis)
128,000 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 124th of 185Claude Opus 5.5 – $1.21 blended, 60th percentilecheapest: Mistral Nemo –
Models priced $1–3 per million tokens 32nd of 34Muse Spark 1.3 – sets this group –
Models with similar intelligence sets this group – $1.21 blended, 92nd percentilecheapest: gpt-oss-20b –
Models from developers based in China 54th of 75MiMo-V2.6-Pro – $1.21 blended, 78th percentilecheapest: Qwen3.5-9B –
Open-weights models 57th of 104MiMo-V2.6-Pro – $1.21 blended, 83rd percentilecheapest: Mistral Nemo –

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 $1–3 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 139th of 159 available · 30th of 31 at its price
BenchmarkQwen3-235B-A22B-Thinking-2507Rank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 0.0% 67th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 12.0% 88th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 7.8% 79th of 104 Grok 4.6 50.7%
Vending-Bench 2Vending-Bench 2: money after a year · reported $-11.34 50th of 53 GPT-6 Astra $15,515
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: has not measured this model.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: 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 119th of 187 available · 30th of 35 at its price
BenchmarkQwen3-235B-A22B-Thinking-2507Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 12.7 124th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 15.9% 112th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 79.0% 98th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 119th of 169 available · 27th of 28 at its price
BenchmarkQwen3-235B-A22B-Thinking-2507Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,400 97th of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 32.4 97th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 83rd of 139 available · 19th of 26 at its price
BenchmarkQwen3-235B-A22B-Thinking-2507Rank among availableBest available
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 40.4% 40th of 68 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

Against Qwen3-235B-A22B-Thinking-2507 at $1.21 blended, Intelligence Index 12.7. "Similar intelligence" means within 4 points or better.

Where to run it

1 host on OpenRouter at the standard service tier, with a median of $1.21 blended per million tokens; quantisation where the host states it: FP8. Cheapest first.

HostQuantisationInputOutputBlended
VeniceFP8$0.45$3.50$1.21

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.

Qwen3-235B-A22B-Thinking-2507Muse Spark 1.3
most intelligent at $1–3 per million tokens
gpt-oss-20b
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
MiMo-V2.6-Pro
most intelligent from China
Price per million tokens $1.21 $2.00$0.06$8.00$0.54
Tokens a second – 2542779643
Intelligence Index 12.7 48.110.057.646.3
Spring Prompt overall – 59–82–
Rank among available models, by use case
Product listings – 17th–13th–
Decks from an analysis – 25th–7th–
User surveys – ––4th–
Marketing planning – 25th–9th–
Agents and tool use 139th of 159 13th130th3rd23rd
Professional work – 8th–3rd–
Reasoning and knowledge 119th of 187 11th132nd1st13th
Writing 119th of 169 7th155th5th23rd
Sticking to the facts 83rd of 139 11th–3rd10th
Speed under pressure – 33rd–––

Shaded figures are better than Qwen3-235B-A22B-Thinking-2507's. A dash means no result.

Where it has been measured

32nd most intelligent of the 34 models priced $1–3 per million tokens. Among models available today, in the bottom quarter for agents and tool use.

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

Every result

23 published results from 5 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 6 results
MeasureValueRankConfigurationDated
Arena Text: business, management and financeArena rating, higher is better 1,404
1,389–1,419
152 of 406 Qwen3-235B-A22B-Thinking-2507 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,371
1,352–1,389
156 of 411 Qwen3-235B-A22B-Thinking-2507 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,466
1,437–1,494
96 of 363 Qwen3-235B-A22B-Thinking-2507 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,385
1,372–1,397
165 of 413 Qwen3-235B-A22B-Thinking-2507 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,400
1,393–1,407
160 of 413 Qwen3-235B-A22B-Thinking-2507 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,377
1,363–1,391
162 of 412 Qwen3-235B-A22B-Thinking-2507 2 Oct 2026

Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Artificial Analysis · reported by Artificial Analysis · 12 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 22.1 150 of 187 Qwen3-235B-A22B-Thinking-2507 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 12.7 283 of 413 Qwen3-235B-A22B-Thinking-2507 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 79.0% 181 of 360 Qwen3-235B-A22B-Thinking-2507 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 15.9% 224 of 419 Qwen3-235B-A22B-Thinking-2507 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 51.2% 135 of 288 Qwen3-235B-A22B-Thinking-2507 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 72.0% 182 of 407 Qwen3-235B-A22B-Thinking-2507 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 41.4% 157 of 205 Qwen3-235B-A22B-Thinking-2507 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 12.0% 157 of 188 Qwen3-235B-A22B-Thinking-2507 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 Qwen3-235B-A22B-Thinking-2507 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 13.6% 182 of 282 Qwen3-235B-A22B-Thinking-2507 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 7.8% 138 of 175 Qwen3-235B-A22B-Thinking-2507 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 53.2% 158 of 286 Qwen3-235B-A22B-Thinking-2507 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 40.4% 45 of 85 Qwen3-235B-A22B-Thinking-2507 27 Aug 2026

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

UGI Leaderboard · reported by UGI Leaderboard · 3 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 30.0% 262 of 379 Qwen3-235B-A22B-Thinking-2507 21 Sep 2025
UGI: style adherencescore from 0 to 1, higher is better 0.31 324 of 379 Qwen3-235B-A22B-Thinking-2507 21 Sep 2025
UGI: writing scorescore out of 100, higher is better 32.4 263 of 379 Qwen3-235B-A22B-Thinking-2507 21 Sep 2025

Not shown: Not other format limits such as character counts or bullet counts.

Vending-Bench 2 · reported by Vending-Bench 2 · 1 result
MeasureValueRankConfigurationDated
Vending-Bench 2: money after a yearUS dollars, higher is better $-11.34 60 of 63 Qwen3-235B-A22B-Thinking-2507 1 Oct 2026

Not shown: Not a real business; one simulated market with set rules.

Will Qwen3-235B-A22B-Thinking-2507 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.