Models / Qwen3.5-122B-A10B

Alibaba

Qwen3.5-122B-A10B

Qwen3.5-122B-A10B is strongest at reasoning and knowledge; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is Gemma 4 26B A4B, at $0.14 per million tokens against $0.72.

Results 16 Nov 2026 · 41 results · 4 sources

Test Qwen3.5-122B-A10B on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.26 in · $2.08 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
144 tokens a second; on its test prompt the answer starts after 1.0 s, thinking time included
Artificial Analysis, on its usual API, at no reasoning; 132–144 across 2 settings
Intelligence Index
17.7
Artificial Analysis, at no reasoning; 15.6–17.7 across 2 settings
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Alibaba, based in China
Weights published
Released
24 Feb 2026 (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 104th of 185Claude Opus 5.5 – $0.72 blended, 48th percentilecheapest: Mistral Nemo 23rd of 65Nemotron 3.5 Super VL
Models priced $0.25–1 per million tokens 28th of 61MiMo-V2.6-Pro – sets this group 11th of 20Gemini 3.5 Flash-Lite
Models with similar intelligence sets this group – $0.72 blended, 61st percentilecheapest: Gemma 4 26B A4B 3rd of 7Mistral Medium 3.5
Models writing 100–200 tokens a second 16th of 21Claude Sonnet 5.5 – $0.72 blended, 55th percentilecheapest: Qwen3.5-9B sets this group
Models from developers based in China 44th of 75MiMo-V2.6-Pro – $0.72 blended, 59th percentilecheapest: Qwen3.5-9B 6th of 23DeepSeek-V4.1-Flash
Open-weights models 44th of 104MiMo-V2.6-Pro – $0.72 blended, 67th percentilecheapest: Mistral Nemo 15th 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 $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 101st of 159 available · 24th of 47 at its price
BenchmarkQwen3.5-122B-A10BRank 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 47.6% 61st of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 15.3% 54th of 104 Grok 4.6 50.7%
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: 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 92nd of 187 available · 20th of 61 at its price
BenchmarkQwen3.5-122B-A10BRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 17.7 104th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 25.2% 90th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 85.7% 67th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 98th of 169 available · 26th of 58 at its price
BenchmarkQwen3.5-122B-A10BRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,416 84th of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 39.5 83rd of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 103rd of 139 available · 22nd of 40 at its price
BenchmarkQwen3.5-122B-A10BRank among availableBest available
Vectara Hallucination LeaderboardVectara: hallucination rate · reported 11.2% 51st of 71 GPT-5.4 nano 3.1%
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,428 80th of 109 Gemini 4 Argon 1,511
  • 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 Qwen3.5-122B-A10B at $0.72 blended, Intelligence Index 17.7. "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 $0.77 blended per million tokens; quantisation where the host states it: FP8, BF16. Cheapest first.

HostQuantisationInputOutputBlended
Alibabanot stated$0.26$2.08$0.72
SiliconFlowFP8$0.26$2.08$0.72
AtlasCloudFP8$0.30$2.40$0.82
NovitaBF16$0.40$3.20$1.10

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.

Qwen3.5-122B-A10BMiMo-V2.6-Pro
most intelligent at $0.25–1 per million tokens
Gemma 4 26B A4B
cheapest with similar intelligence
Mistral Medium 3.5
fastest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $0.72 $0.54$0.14$3.00$8.00
Tokens a second 144 438215796
Intelligence Index 17.7 46.316.714.257.6
Spring Prompt overall – ––1582
Rank among available models, by use case
Product listings – ––23rd13th
Decks from an analysis – ––31st7th
User surveys – ––21st4th
Marketing planning – ––32nd9th
Agents and tool use 101st of 159 23rd105th100th3rd
Professional work – –––3rd
Reasoning and knowledge 92nd of 187 13th110th123rd1st
Writing 98th of 169 23rd82nd85th5th
Sticking to the facts 103rd of 139 10th43rd98th3rd
Speed under pressure – ––10th–

Shaded figures are better than Qwen3.5-122B-A10B's. A dash means no result.

Where it has been measured

28th 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.

Every result

41 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 1,428
1,424–1,431
121 of 182 Qwen3.5-122B-A10B 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,422
1,413–1,430
122 of 406 Qwen3.5-122B-A10B 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,366
1,356–1,375
159 of 411 Qwen3.5-122B-A10B 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,442
1,430–1,453
128 of 363 Qwen3.5-122B-A10B 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,406
1,399–1,412
134 of 413 Qwen3.5-122B-A10B 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,416
1,412–1,420
135 of 413 Qwen3.5-122B-A10B 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,387
1,380–1,395
147 of 412 Qwen3.5-122B-A10B 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 · 26 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 45.7 109 of 187 Qwen3.5-122B-A10B 20 Oct 2026
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 43.3 117 of 187 Qwen3.5-122B-A10B (no reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 15.6 246 of 413 Qwen3.5-122B-A10B 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 17.7 231 of 413 Qwen3.5-122B-A10B (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 85.7% 118 of 360 Qwen3.5-122B-A10B 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 82.7% 153 of 360 Qwen3.5-122B-A10B (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 25.2% 178 of 419 Qwen3.5-122B-A10B 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 15.9% 224 of 419 Qwen3.5-122B-A10B (no reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 75.7% 24 of 288 Qwen3.5-122B-A10B 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 50.8% 137 of 288 Qwen3.5-122B-A10B (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 76.3% 142 of 407 Qwen3.5-122B-A10B 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 61.3% 248 of 407 Qwen3.5-122B-A10B (no reasoning) 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 132 50 of 137 Qwen3.5-122B-A10B 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 144 41 of 137 Qwen3.5-122B-A10B (no reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 39.7% 166 of 205 Qwen3.5-122B-A10B 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 47.6% 111 of 188 Qwen3.5-122B-A10B 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 47.2% 112 of 188 Qwen3.5-122B-A10B (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 Qwen3.5-122B-A10B 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 31.1% 103 of 282 Qwen3.5-122B-A10B 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 29.5% 111 of 282 Qwen3.5-122B-A10B (no reasoning) 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 16.2 79 of 137 Qwen3.5-122B-A10B 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 0.99 27 of 137 Qwen3.5-122B-A10B (no reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 15.3% 102 of 175 Qwen3.5-122B-A10B 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 10.3% 122 of 175 Qwen3.5-122B-A10B (no reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 93.6% 38 of 286 Qwen3.5-122B-A10B 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 84.5% 86 of 286 Qwen3.5-122B-A10B (no reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

UGI Leaderboard · reported by UGI Leaderboard · 6 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 20.0% 187 of 379 Qwen3.5-122B-A10B (no reasoning) 25 Feb 2026
UGI: requested-length error% off the requested word count, lower is better 9.0% 75 of 379 Qwen3.5-122B-A10B (thinking reasoning) 25 Feb 2026
UGI: style adherencescore from 0 to 1, higher is better 0.36 157 of 379 Qwen3.5-122B-A10B (no reasoning) 25 Feb 2026
UGI: style adherencescore from 0 to 1, higher is better 0.35 166 of 379 Qwen3.5-122B-A10B (thinking reasoning) 25 Feb 2026
UGI: writing scorescore out of 100, higher is better 39.5 226 of 379 Qwen3.5-122B-A10B (no reasoning) 25 Feb 2026
UGI: writing scorescore out of 100, higher is better 38.7 232 of 379 Qwen3.5-122B-A10B (thinking reasoning) 25 Feb 2026

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

Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
MeasureValueRankConfigurationDated
Vectara: answer rate% of documents, higher is better 99.8% 34 of 108 Qwen3.5-122B-A10B 22 Sep 2026
Vectara: hallucination rate% of summaries, lower is better 11.2% 73 of 108 Qwen3.5-122B-A10B 22 Sep 2026

Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.

Will Qwen3.5-122B-A10B 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.