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

Alibaba

Qwen3-VL-235B-A22B-Instruct

Qwen3-VL-235B-A22B-Instruct 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 Llama 3.1 8B Instruct, at $0.06 per million tokens against $0.63.

Results 5 Nov 2026 · 17 results · 3 sources

Price per million tokens
$0.21 in · $1.90 out
Typical host on OpenRouter, 5 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
9.9
Artificial Analysis
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Alibaba, based in China
Weights published
Released
23 Sep 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 139th of 188Claude Opus 5.5 – $0.63 blended, 46th percentilecheapest: Mistral Nemo –
Models priced $0.25–1 per million tokens 45th of 64MiMo-V2.6-Pro – sets this group –
Models with similar intelligence sets this group – $0.63 blended, 66th percentilecheapest: Llama 3.1 8B Instruct –
Models from developers based in China 62nd of 77MiMo-V2.6-Pro – $0.63 blended, 58th percentilecheapest: Qwen3.5-9B –
Open-weights models 69th of 106MiMo-V2.6-Pro – $0.63 blended, 64th 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 Not measured
  • 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.
  • 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 140th of 188 available · 46th of 64 at its price
BenchmarkQwen3-VL-235B-A22B-InstructRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 9.9 139th of 188 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 6.6% 141st of 187 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 71.2% 118th of 171 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 92nd of 173 available · 22nd of 62 at its price
BenchmarkQwen3-VL-235B-A22B-InstructRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,413 89th of 156 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 43.0 70th of 126 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 120th of 143 available · 30th of 44 at its price
BenchmarkQwen3-VL-235B-A22B-InstructRank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,415 89th of 112 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-VL-235B-A22B-Instruct at $0.63 blended, Intelligence Index 9.9. "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 $0.63 blended per million tokens; quantisation where the host states it: FP8. Cheapest first.

HostQuantisationInputOutputBlended
DeepInfraFP8$0.20$0.88$0.37
ParasailFP8$0.21$1.90$0.63
VeniceFP8$0.21$1.90$0.63

Prices per million tokens from OpenRouter's public endpoint list, checked 5 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-VL-235B-A22B-InstructMiMo-V2.6-Pro
most intelligent at $0.25–1 per million tokens
Llama 3.1 8B Instruct
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $0.63 $0.54$0.06$8.00
Tokens a second – 43–96
Intelligence Index 9.9 46.36.957.6
Spring Prompt overall – ––84
Rank among available models, by use case
Product listings – ––10th
Decks from an analysis – ––4th
User surveys – ––3rd
Marketing planning – ––7th
Agents and tool use – 19th154th2nd
Professional work – ––3rd
Reasoning and knowledge 140th of 188 12th166th1st
Writing 92nd of 173 22nd168th5th
Sticking to the facts 120th of 143 10th–3rd
Speed under pressure – –––

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

Where it has been measured

45th most intelligent of the 64 models priced $0.25–1 per million tokens. Among models available today, in the bottom quarter for sticking to the facts.

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

Every result

17 published results from 3 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 1,415
1,397–1,432
140 of 182 Qwen3-VL-235B-A22B-Instruct 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,440
1,426–1,454
102 of 406 Qwen3-VL-235B-A22B-Instruct 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,358
1,341–1,375
169 of 411 Qwen3-VL-235B-A22B-Instruct 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,440
1,415–1,465
130 of 363 Qwen3-VL-235B-A22B-Instruct 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,409
1,398–1,421
130 of 413 Qwen3-VL-235B-A22B-Instruct 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,413
1,407–1,420
143 of 413 Qwen3-VL-235B-A22B-Instruct 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,387
1,374–1,400
146 of 412 Qwen3-VL-235B-A22B-Instruct 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 9.9 320 of 413 Qwen3-VL-235B-A22B-Instruct 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 71.2% 242 of 360 Qwen3-VL-235B-A22B-Instruct 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 6.6% 313 of 411 Qwen3-VL-235B-A22B-Instruct 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 42.7% 189 of 288 Qwen3-VL-235B-A22B-Instruct 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 32.7% 323 of 399 Qwen3-VL-235B-A22B-Instruct 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 6.8% 215 of 282 Qwen3-VL-235B-A22B-Instruct 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 35.1% 191 of 286 Qwen3-VL-235B-A22B-Instruct 20 Oct 2026

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

UGI Leaderboard · reported by UGI Leaderboard · 3 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 19.0% 171 of 379 Qwen3-VL-235B-A22B-Instruct 24 Feb 2026
UGI: style adherencescore from 0 to 1, higher is better 0.36 162 of 379 Qwen3-VL-235B-A22B-Instruct 24 Feb 2026
UGI: writing scorescore out of 100, higher is better 43.0 201 of 379 Qwen3-VL-235B-A22B-Instruct 24 Feb 2026

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

Test Qwen3-VL-235B-A22B-Instruct on your own prompt.

Benchmarks aren't your task. Run it next to cheaper and newer models on your prompt, with every answer checked and costed.