Models / Qwen3-Next-80B-A3B-Instruct
Qwen3-Next-80B-A3B-Instruct
Qwen3-Next-80B-A3B-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 gpt-oss-20b, at $0.06 per million tokens against $0.34.
Results 16 Nov 2026 · 19 results · 3 sources
Test Qwen3-Next-80B-A3B-Instruct on your prompt → It runs beside the models you could use instead, with every answer checked and costed.
- Price per million tokens
- $0.09 in · $1.10 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices - Speed
- 121 tokens a second; on its test prompt the answer starts after 0.6 s, thinking time included
Artificial Analysis, on its usual API - Intelligence Index
- 9.6
Artificial Analysis - Spring Prompt overall
- Not ranked yet
needs our benchmarks and two groups of results - Developer
- Alibaba, based in China
Weights published - Released
- 11 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.
| Among | Intelligence Index | Spring Prompt overall | Price, blended | Speed |
|---|---|---|---|---|
| Models available today | 138th of 185Claude Opus 5.5 | – | $0.34 blended, 30th percentilecheapest: Mistral Nemo | 32nd of 65Nemotron 3.5 Super VL |
| Models priced $0.25–1 per million tokens | 44th of 61MiMo-V2.6-Pro | – | sets this group | 13th of 20Gemini 3.5 Flash-Lite |
| Models with similar intelligence | sets this group | – | $0.34 blended, 48th percentilecheapest: gpt-oss-20b | 8th of 17gpt-oss-20b |
| Models writing 100–200 tokens a second | 20th of 21Claude Sonnet 5.5 | – | $0.34 blended, 40th percentilecheapest: Qwen3.5-9B | sets this group |
| Models from developers based in China | 62nd of 75MiMo-V2.6-Pro | – | $0.34 blended, 31st percentilecheapest: Qwen3.5-9B | 8th of 23DeepSeek-V4.1-Flash |
| Open-weights models | 69th of 104MiMo-V2.6-Pro | – | $0.34 blended, 44th percentilecheapest: Mistral Nemo | 19th 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
- CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is
- DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled
- SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending
- ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls
- 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
- 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
| Benchmark | Qwen3-Next-80B-A3B-Instruct | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported | 9.6 | 138th of 185 | Claude Opus 5.5 57.6 |
| Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported | 7.6% | 133rd of 186 | Claude Opus 5.5 61.4% |
| Artificial AnalysisArtificial Analysis: GPQA Diamond · reported | 73.8% | 110th of 168 | GPT-6 Astra 96.3% |
WritingWhat people prefer in blind comparisons, and judged writing quality
| Benchmark | Qwen3-Next-80B-A3B-Instruct | Rank among available | Best available |
|---|---|---|---|
| Arena (formerly LMArena)Arena Text: overall · reported | 1,399 | 98th of 153 | Gemini 4 Argon 1,525 |
| UGI LeaderboardUGI: writing score · reported | 41.8 | 75th of 124 | Gemini 3.8 Flash 78.6 |
Sticking to the factsSummarising without inventing things, and factual answers
| Benchmark | Qwen3-Next-80B-A3B-Instruct | Rank among available | Best available |
|---|---|---|---|
| Arena (formerly LMArena)Arena Text factuality: overall · reported | 1,419 | 85th 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)
- BulletBench: has not measured this model.
Nearest alternatives
- Cheaper at similar intelligencegpt-oss-20b$0.06 blended · Intelligence Index 10.0Compare with Qwen3-Next-80B-A3B-Instruct →
- Alibaba's newer, at least as capable modelQwen3.8-Max (0902)$3.00 blended · Intelligence Index 45.4Compare with Qwen3-Next-80B-A3B-Instruct →
Against Qwen3-Next-80B-A3B-Instruct at $0.34 blended, Intelligence Index 9.6. "Similar intelligence" means within 4 points or better.
Where to run it
2 hosts on OpenRouter at the standard service tier, with a median of $0.35 blended per million tokens; quantisation where the host states it: FP8. Cheapest first.
| Host | Quantisation | Input | Output | Blended |
|---|---|---|---|---|
| DeepInfra | FP8 | $0.09 | $1.10 | $0.34 |
| Parasail | FP8 | $0.10 | $1.10 | $0.35 |
Other service tiers, not counted above: DeepInfra flex $0.07 in, $0.88 out; DeepInfra priority $0.14 in, $1.65 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.
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-Next-80B-A3B-Instruct | MiMo-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 | $0.34 | $0.54 | $0.06 | $8.00 |
| Tokens a second | 121 | 43 | 277 | 96 |
| Intelligence Index | 9.6 | 46.3 | 10.0 | 57.6 |
| 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 | – | 23rd | 130th | 3rd |
| Professional work | – | – | – | 3rd |
| Reasoning and knowledge | 135th of 187 | 13th | 132nd | 1st |
| Writing | 102nd of 169 | 23rd | 155th | 5th |
| Sticking to the facts | 114th of 139 | 10th | – | 3rd |
| Speed under pressure | – | – | – | – |
| Side by side → | Side by side → | Side by side → | ||
Shaded figures are better than Qwen3-Next-80B-A3B-Instruct's. A dash means no result.
Where it has been measured
44th most intelligent of the 61 models priced $0.25–1 per million tokens. Among models available today, in the bottom quarter for sticking to the facts.
- Arena (formerly LMArena)7 results
- Artificial Analysis9 results
- UGI Leaderboard3 results
- BulletBenchNot measured
- CatalogBenchNot measured
- DeckBenchNot measured
- ROASBenchNot measured
- SurveyBenchNot measured
- APEX-AgentsNot measured
- Berkeley Function Calling Leaderboard (BFCL) V4Not measured
- GDP.pdfNot measured
- Microsoft STATE-BenchNot measured
- OpenHands IndexNot measured
- Remote Labor IndexNot measured
- SimpleQA Verified (Epoch AI)Not measured
- tau2-benchNot measured
- Vectara Hallucination LeaderboardNot measured
- Vending-Bench 2Not measured
Every result
19 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
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Arena Text factuality: overallArena rating, higher is better | 1,419 1,412–1,425 |
132 of 182 | Qwen3-Next-80B-A3B-Instruct | 2 Oct 2026 |
| Arena Text: business, management and financeArena rating, higher is better | 1,412 1,403–1,421 |
140 of 406 | Qwen3-Next-80B-A3B-Instruct | 2 Oct 2026 |
| Arena Text: creative writingArena rating, higher is better | 1,313 1,302–1,324 |
215 of 411 | Qwen3-Next-80B-A3B-Instruct | 2 Oct 2026 |
| Arena Text: expert promptsArena rating, higher is better | 1,400 1,382–1,417 |
177 of 363 | Qwen3-Next-80B-A3B-Instruct | 2 Oct 2026 |
| Arena Text: instruction followingArena rating, higher is better | 1,376 1,369–1,384 |
178 of 413 | Qwen3-Next-80B-A3B-Instruct | 2 Oct 2026 |
| Arena Text: overallArena rating, higher is better | 1,399 1,394–1,404 |
161 of 413 | Qwen3-Next-80B-A3B-Instruct | 2 Oct 2026 |
| Arena Text: writing, literature and languageArena rating, higher is better | 1,342 1,334–1,351 |
199 of 412 | Qwen3-Next-80B-A3B-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 · 9 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 9.6 | 325 of 413 | Qwen3-Next-80B-A3B-Instruct | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 73.8% | 226 of 360 | Qwen3-Next-80B-A3B-Instruct | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 7.6% | 303 of 419 | Qwen3-Next-80B-A3B-Instruct | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 39.7% | 207 of 288 | Qwen3-Next-80B-A3B-Instruct | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 52.7% | 274 of 407 | Qwen3-Next-80B-A3B-Instruct | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 121 | 54 of 137 | Qwen3-Next-80B-A3B-Instruct | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 7.6% | 208 of 282 | Qwen3-Next-80B-A3B-Instruct | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 0.57 | 10 of 137 | Qwen3-Next-80B-A3B-Instruct | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 21.6% | 250 of 286 | Qwen3-Next-80B-A3B-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
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| UGI: requested-length error% off the requested word count, lower is better | 7.0% | 56 of 379 | Qwen3-Next-80B-A3B-Instruct | 29 Nov 2025 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.31 | 328 of 379 | Qwen3-Next-80B-A3B-Instruct | 29 Nov 2025 |
| UGI: writing scorescore out of 100, higher is better | 41.8 | 208 of 379 | Qwen3-Next-80B-A3B-Instruct | 29 Nov 2025 |
Not shown: Not other format limits such as character counts or bullet counts.
Will Qwen3-Next-80B-A3B-Instruct 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.