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

Alibaba

Qwen3-235B-A22B-Instruct-2507

Qwen3-235B-A22B-Instruct-2507 is strongest at agents and tool use; 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 $0.30.

Results 16 Nov 2026 · 33 results · 4 sources

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

Price per million tokens
$0.15 in · $0.75 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
12.0
Artificial Analysis
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Alibaba, based in China
Weights published
Released
21 Jul 2025 (Artificial Analysis)
262,144 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 127th of 185Claude Opus 5.5 – $0.30 blended, 27th percentilecheapest: Mistral Nemo –
Models priced $0.25–1 per million tokens 36th of 61MiMo-V2.6-Pro – sets this group –
Models with similar intelligence sets this group – $0.30 blended, 33rd percentilecheapest: gpt-oss-20b –
Models from developers based in China 56th of 75MiMo-V2.6-Pro – $0.30 blended, 23rd percentilecheapest: Qwen3.5-9B –
Open-weights models 59th of 104MiMo-V2.6-Pro – $0.30 blended, 38th 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 $0.25–1 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 52nd of 159 available · 6th of 47 at its price
BenchmarkQwen3-235B-A22B-Instruct-2507Rank among availableBest available
Berkeley Function Calling Leaderboard (BFCL) V4BFCL: overall accuracy · reported 52.2% 12th of 36 Claude Opus 4.5 77.5%
  • tau2-bench: has not measured this model.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
  • Artificial Analysis: has not measured this model.
  • 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 126th of 187 available · 36th of 61 at its price
BenchmarkQwen3-235B-A22B-Instruct-2507Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 12.0 127th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 11.1% 124th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 75.3% 108th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 84th of 169 available · 17th of 58 at its price
BenchmarkQwen3-235B-A22B-Instruct-2507Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,422 78th of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 49.0 60th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 95th of 139 available · 20th of 40 at its price
BenchmarkQwen3-235B-A22B-Instruct-2507Rank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,431 74th of 109 Gemini 4 Argon 1,511
  • Vectara Hallucination Leaderboard: 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

Against Qwen3-235B-A22B-Instruct-2507 at $0.30 blended, Intelligence Index 12.0. "Similar intelligence" means within 4 points or better.

Where to run it

3 hosts on OpenRouter at the standard service tier, with a median of $0.30 blended per million tokens; quantisation where the host states it: FP8. Cheapest first.

HostQuantisationInputOutputBlended
DeepInfraFP8$0.09$0.55$0.21
VeniceFP8$0.15$0.75$0.30
ParasailFP8$0.14$0.80$0.31

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-Instruct-2507MiMo-V2.6-Pro
most intelligent at $0.25–1 per million tokens
gpt-oss-20b
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $0.30 $0.54$0.06$8.00
Tokens a second – 4327796
Intelligence Index 12.0 46.310.057.6
Spring Prompt overall – ––82
Rank among available models, by use case
Product listings – ––13th
Decks from an analysis – ––7th
User surveys – ––4th
Marketing planning – ––9th
Agents and tool use 52nd of 159 23rd130th3rd
Professional work – ––3rd
Reasoning and knowledge 126th of 187 13th132nd1st
Writing 84th of 169 23rd155th5th
Sticking to the facts 95th of 139 10th–3rd
Speed under pressure – –––

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

Where it has been measured

36th most intelligent of the 61 models priced $0.25–1 per million tokens. Among models available today, mid-field on every use case measured so far.

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

Every result

33 published results from 4 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 7 results
MeasureValueRankConfigurationDated
Arena Text factuality: overallArena rating, higher is better 1,431
1,429–1,434
111 of 182 Qwen3-235B-A22B-Instruct-2507 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,432
1,427–1,437
112 of 406 Qwen3-235B-A22B-Instruct-2507 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,378
1,373–1,384
144 of 411 Qwen3-235B-A22B-Instruct-2507 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,447
1,440–1,455
120 of 363 Qwen3-235B-A22B-Instruct-2507 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,414
1,410–1,418
123 of 413 Qwen3-235B-A22B-Instruct-2507 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,422
1,420–1,425
126 of 413 Qwen3-235B-A22B-Instruct-2507 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,396
1,392–1,401
136 of 412 Qwen3-235B-A22B-Instruct-2507 2 Oct 2026

Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.

Artificial Analysis · reported by Artificial Analysis · 7 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 12.0 292 of 413 Qwen3-235B-A22B-Instruct-2507 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 75.3% 214 of 360 Qwen3-235B-A22B-Instruct-2507 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 11.1% 268 of 419 Qwen3-235B-A22B-Instruct-2507 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 46.1% 160 of 288 Qwen3-235B-A22B-Instruct-2507 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 33.9% 329 of 407 Qwen3-235B-A22B-Instruct-2507 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 15.2% 173 of 282 Qwen3-235B-A22B-Instruct-2507 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 33.3% 199 of 286 Qwen3-235B-A22B-Instruct-2507 20 Oct 2026

Not shown: Not business work, and a blend: read the parts for any one task.

Berkeley Function Calling Leaderboard (BFCL) V4 · reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 16 results
MeasureValueRankConfigurationDated
BFCL: irrelevance detection% correct, higher is better 81.7% 50 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl fc) 16 Dec 2025
BFCL: irrelevance detection% correct, higher is better 78.9% 65 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl prompt) 16 Dec 2025
BFCL: memory% correct, higher is better 23.9% 35 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl fc) 16 Dec 2025
BFCL: memory% correct, higher is better 19.4% 46 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl prompt) 16 Dec 2025
BFCL: multi-turn tasks% correct, higher is better 45.4% 21 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl fc) 16 Dec 2025
BFCL: multi-turn tasks% correct, higher is better 44.6% 23 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl prompt) 16 Dec 2025
BFCL: overall accuracy% correct, higher is better 48.0% 31 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl fc) 16 Dec 2025
BFCL: overall accuracy% correct, higher is better 52.2% 23 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl prompt) 16 Dec 2025
BFCL: relevance detection% correct, higher is better 87.5% 27 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl fc) 16 Dec 2025
BFCL: relevance detection% correct, higher is better 93.8% 8 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl prompt) 16 Dec 2025
BFCL: single-turn calls (curated)% correct, higher is better 37.4% 104 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl fc) 16 Dec 2025
BFCL: single-turn calls (curated)% correct, higher is better 90.3% 2 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl prompt) 16 Dec 2025
BFCL: single-turn calls (user-contributed)% correct, higher is better 68.9% 64 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl fc) 16 Dec 2025
BFCL: single-turn calls (user-contributed)% correct, higher is better 78.7% 19 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl prompt) 16 Dec 2025
BFCL: web search% correct, higher is better 54.0% 25 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl fc) 16 Dec 2025
BFCL: web search% correct, higher is better 50.5% 26 of 109 Qwen3-235B-A22B-Instruct-2507 (bfcl prompt) 16 Dec 2025

Not shown: Not general refusal or safety behaviour.

UGI Leaderboard · reported by UGI Leaderboard · 3 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 15.0% 127 of 379 Qwen3-235B-A22B-Instruct-2507 21 Sep 2025
UGI: style adherencescore from 0 to 1, higher is better 0.36 133 of 379 Qwen3-235B-A22B-Instruct-2507 21 Sep 2025
UGI: writing scorescore out of 100, higher is better 49.0 173 of 379 Qwen3-235B-A22B-Instruct-2507 21 Sep 2025

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

Will Qwen3-235B-A22B-Instruct-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.