Models / Qwen3.5-9B
Qwen3.5-9B
Qwen3.5-9B 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 $0.11.
Results 16 Nov 2026 · 31 results · 2 sources
Test Qwen3.5-9B on your prompt → It runs beside the models you could use instead, with every answer checked and costed.
- Price per million tokens
- $0.10 in · $0.15 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices - Speed
- 110 tokens a second; on its test prompt the answer starts after 0.4 s, thinking time included
Artificial Analysis, on its usual API, at no reasoning; 71–110 across 2 settings - Intelligence Index
- 13.3
Artificial Analysis, at no reasoning; 11.2–13.3 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
- 2 Mar 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.
| Among | Intelligence Index | Spring Prompt overall | Price, blended | Speed |
|---|---|---|---|---|
| Models available today | 118th of 185Claude Opus 5.5 | – | $0.11 blended, 7th percentilecheapest: Mistral Nemo | 35th of 65Nemotron 3.5 Super VL |
| Models priced under $0.25 per million tokens | 12th of 41Claude Haiku 5.5 | – | sets this group | 10th of 19Nemotron 3.5 Super VL |
| Models with similar intelligence | sets this group | – | $0.11 blended, 5th percentilecheapest: gpt-oss-20b | 7th of 11gpt-oss-20b |
| Models writing 100–200 tokens a second | 18th of 21Claude Sonnet 5.5 | – | $0.11 blended, 0th percentilethe cheapest | sets this group |
| Models from developers based in China | 51st of 75MiMo-V2.6-Pro | – | $0.11 blended, 0th percentilethe cheapest | 9th of 23DeepSeek-V4.1-Flash |
| Open-weights models | 53rd of 104MiMo-V2.6-Pro | – | $0.11 blended, 10th percentilecheapest: Mistral Nemo | 20th 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 under $0.25 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
| Benchmark | Qwen3.5-9B | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported | 0.5% | 62nd of 107 | Kimi K3.1 Pro 67.2% |
| Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported | 29.2% | 77th of 107 | Claude Fable 5.1 91.4% |
| Artificial AnalysisArtificial Analysis: τ-bench banking · reported | 7.0% | 82nd 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
- 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 | Qwen3.5-9B | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported | 13.3 | 118th of 185 | Claude Opus 5.5 57.6 |
| Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported | 14.9% | 114th of 186 | Claude Opus 5.5 61.4% |
| Artificial AnalysisArtificial Analysis: GPQA Diamond · reported | 80.6% | 93rd of 168 | GPT-6 Astra 96.3% |
WritingWhat people prefer in blind comparisons, and judged writing quality
| Benchmark | Qwen3.5-9B | Rank among available | Best available |
|---|---|---|---|
| UGI LeaderboardUGI: writing score · reported | 39.5 | 84th of 124 | Gemini 3.8 Flash 78.6 |
- Arena (formerly LMArena): has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers
- Vectara Hallucination Leaderboard: has not measured this model.
- Arena (formerly LMArena): 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 Qwen3.5-9B →
- Alibaba's newer, at least as capable modelQwen3.8-Max (0902)$3.00 blended · Intelligence Index 45.4
Against Qwen3.5-9B at $0.11 blended, Intelligence Index 13.3. "Similar intelligence" means within 4 points or better.
Where to run it
6 hosts on OpenRouter at the standard service tier, with a median of $0.12 blended per million tokens; quantisation where the host states it: FP4, BF16, FP8. Cheapest first.
| Host | Quantisation | Input | Output | Blended |
|---|---|---|---|---|
| Darkbloom | FP4 | $0.08 | $0.13 | $0.09 |
| DeepInfra | BF16 | $0.10 | $0.15 | $0.11 |
| SiliconFlow | FP8 | $0.10 | $0.15 | $0.11 |
| Parasail | BF16 | $0.10 | $0.25 | $0.14 |
| PrimeIntellect | BF16 | $0.15 | $0.23 | $0.17 |
| Together | not stated | $0.17 | $0.25 | $0.19 |
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.
| Qwen3.5-9B | Claude Haiku 5.5 most intelligent at under $0.25 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 | $0.11 | $0.20 | $0.06 | $8.00 | $0.54 |
| Tokens a second | 110 | 240 | 277 | 96 | 43 |
| Intelligence Index | 13.3 | 43.4 | 10.0 | 57.6 | 46.3 |
| Spring Prompt overall | – | 40 | – | 82 | – |
| Rank among available models, by use case | |||||
| Product listings | – | 20th | – | 13th | – |
| Decks from an analysis | – | 18th | – | 7th | – |
| User surveys | – | 7th | – | 4th | – |
| Marketing planning | – | 30th | – | 9th | – |
| Agents and tool use | 111th of 159 | 28th | 130th | 3rd | 23rd |
| Professional work | – | – | – | 3rd | – |
| Reasoning and knowledge | 116th of 187 | 25th | 132nd | 1st | 13th |
| Writing | 112th of 169 | – | 155th | 5th | 23rd |
| Sticking to the facts | – | – | – | 3rd | 10th |
| Speed under pressure | – | 21st | – | – | – |
| Side by side → | Side by side → | ||||
Shaded figures are better than Qwen3.5-9B's. A dash means no result.
Where it has been measured
Cheapest of the 88 models from developers based in China, and cheapest of the 21 models writing 100–200 tokens a second. 12th most intelligent of the 41 models priced under $0.25 per million tokens. Among models available today, mid-field on every use case measured so far.
- Artificial Analysis25 results
- UGI Leaderboard6 results
- Berkeley Function Calling Leaderboard (BFCL) V4Pending: latest results 16 Dec 2025
- BulletBenchNot measured
- CatalogBenchNot measured
- DeckBenchNot measured
- ROASBenchNot measured
- SurveyBenchNot measured
- APEX-AgentsNot measured
- Arena (formerly LMArena)Not 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
31 published results from 2 sources, each in the source's own units, with the configuration that produced it.
Artificial Analysis · reported by Artificial Analysis · 25 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better | 28.7 | 138 of 187 | Qwen3.5-9B | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better | 23.5 | 145 of 187 | Qwen3.5-9B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 11.2 | 303 of 413 | Qwen3.5-9B | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 13.3 | 274 of 413 | Qwen3.5-9B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 80.6% | 172 of 360 | Qwen3.5-9B | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 78.6% | 186 of 360 | Qwen3.5-9B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 14.9% | 233 of 419 | Qwen3.5-9B | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 9.4% | 288 of 419 | Qwen3.5-9B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 66.7% | 81 of 288 | Qwen3.5-9B | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 37.8% | 221 of 288 | Qwen3.5-9B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 70.0% | 199 of 407 | Qwen3.5-9B | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 46.0% | 291 of 407 | Qwen3.5-9B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 70.8 | 96 of 137 | Qwen3.5-9B | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 110 | 62 of 137 | Qwen3.5-9B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 29.5% | 194 of 205 | Qwen3.5-9B | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better | 29.2% | 135 of 188 | Qwen3.5-9B | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better | 21.3% | 143 of 188 | Qwen3.5-9B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 0.5% | 143 of 204 | Qwen3.5-9B | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 24.2% | 132 of 282 | Qwen3.5-9B | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 18.2% | 155 of 282 | Qwen3.5-9B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 29.1 | 97 of 137 | Qwen3.5-9B | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 0.43 | 4 of 137 | Qwen3.5-9B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ-bench banking% of tasks, higher is better | 7.0% | 141 of 175 | Qwen3.5-9B | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 86.8% | 68 of 286 | Qwen3.5-9B | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 85.1% | 78 of 286 | Qwen3.5-9B (no reasoning) | 20 Oct 2026 |
Not shown: Not your codebase or tools.
UGI Leaderboard · reported by UGI Leaderboard · 6 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| UGI: requested-length error% off the requested word count, lower is better | 15.0% | 127 of 379 | Qwen3.5-9B (think-prefill reasoning) | 15 Mar 2026 |
| UGI: requested-length error% off the requested word count, lower is better | 21.0% | 203 of 379 | Qwen3.5-9B (no reasoning) | 14 Mar 2026 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.31 | 331 of 379 | Qwen3.5-9B (think-prefill reasoning) | 15 Mar 2026 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.32 | 293 of 379 | Qwen3.5-9B (no reasoning) | 14 Mar 2026 |
| UGI: writing scorescore out of 100, higher is better | 39.5 | 227 of 379 | Qwen3.5-9B (think-prefill reasoning) | 15 Mar 2026 |
| UGI: writing scorescore out of 100, higher is better | 33.5 | 255 of 379 | Qwen3.5-9B (no reasoning) | 14 Mar 2026 |
Not shown: Not other format limits such as character counts or bullet counts.
Will Qwen3.5-9B 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.