Data as of November 13, 2026 · How the score is built
Decision readingQwen3.6 Plus scores 53.4 out of 100 and ranks #76 of 215. This profile shows 52 source-displayable benchmark rows; its strongest eligible category is Multilingual at #4. No comparable first-party API price is published in the catalog.
Email me when its price, rank or availability changes.
Capability
53.4/100
field median 49.4#76 of 215 ranked models
Public
#76of 215
Verified #44 of 81
Price
API rate not published
input median $0.60No comparable first-party hosted token rate
Speed
56tok/s
field median 92 tok/sFirst token 100.68 s
Context
1Mtokens
field median 256,000Reported for this model; direct source link not stored
Decision snapshot
Where this model sits in the ranked field, its strongest published evidence, and what to validate before choosing it. The marker compares it with the current ranked catalog, not with an absolute quality threshold.
Strongest published evidence
Multilingual ranks #4. A well-rounded choice across a range of tasks.
Validate before choosing
52 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 52 displayable benchmark rows
Is Qwen3.6 Plus right for your job?
Its place on the LLM Selector’s job rankings, the same order the job pages publish. Describe your own job to see where it stands for that.
Qwen3.6 Plus has a newer version, Qwen3.7 Plus. Where Qwen3.7 Plus ranks by benchmark score:
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #87 of 135Percentile 36thWeight 22%13 benchmarksVerified | 34.3 | 13 benchmarks | Verified | |||
| CodingRank #72 of 162Percentile 56thWeight 20%9 benchmarksMixed sources | 39.8 | 9 benchmarks | Mixed sources | |||
| ReasoningRank #98 of 160Percentile 39thWeight 17%2 benchmarksVerified | 35.6 | 2 benchmarks | Verified | |||
| MultimodalRank #46 of 67Percentile 32ndWeight 12%7 benchmarksMixed sources | 55.2 | 7 benchmarks | Mixed sources | |||
| KnowledgeRank #66 of 180Percentile 64thWeight 12%8 benchmarksVerified | 53.1 | 8 benchmarks | Verified | |||
| MultilingualRank #4 of 17Percentile 81stWeight 7%2 benchmarksVerified | 93.8 | 2 benchmarks | Verified | |||
| Inst. FollowingRank #50 of 157Percentile 69thWeight 5%2 benchmarksVerified | 85.8 | 2 benchmarks | Verified | |||
| MathRank #6 of 12Percentile 55thWeight 5%6 benchmarksVerified | 62.3 | 6 benchmarks | Verified |
52 of 919 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic13/13 verified
- Coding8/9 verified
- Reasoning2/2 verified
- Multimodal6/7 verified
- Knowledge8/8 verified
- Multilingual2/2 verified
- Inst. Following2/2 verified
- Math6/6 verified
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
Qwen3.6 Plus category percentile values
- Agentic36th percentile
- Coding56th percentile
- Reasoning39th percentile
- Multimodal32nd percentile
- Knowledge64th percentile
- Multilingual81st percentile
- Instruction following69th percentile
- Math55th percentile
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#87/135
- Coding#72/162
- Reasoning#98/160
- Multimodal#46/67
- Knowledge#66/180
- Multilingual#4/17
- Inst. Following#50/157
- Math#6/12
Benchmark ledger
Every result says who ran the test. For this model, Alibaba ran 37 of 52. Coding opens by default. The tick marks the best source-verified result in the catalog; provisional leaders do not set the reference.
Coding9 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| SWE-bench Pro | 56.6% | Best verified: Claude Fable 5.2 · 93% | Gap36.4 behind | Reported by Alibaba | Counts26% ref. weight |
| LiveCodeBench (Vals)LiveCodeBench, Vals AI run | 86.0% | Best verified: Claude Fable 5.1 · 90.5% | Gap4.5 behind | Independent run: Vals AI | Counts8% ref. weight |
| SWE Multilingual | 73.8% | Best verified: Claude Fable 5.2 · 96.6% | Gap22.8 behind | Reported by Alibaba | Counts5% ref. weight |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | 78.8% | Best verified: Claude Opus 5 · 96% | Gap17.2 behind | Reported by Alibaba | Shown only |
| LiveCodeBench v6 | 87.1% | Best verified: Sakana Fugu-Ultra · 93.2% | Gap6.1 behind | Reported by Alibaba | Shown only |
| NL2Repo | 37.9% | Best verified: DeepSeek V4.1 Flash 1017 · 68.2% | Gap30.3 behind | Another lab’s comparison table | Shown only |
| Terminal-Bench 2.0 | 61.6% | Best verified: GPT-5.5 · 82.0% | Gap20.4 behind | Reported by Alibaba | Shown only |
| Vibe Code BenchVibe Code Bench v1.1 | 25.56% | Best verified: Gemini 4 Argon · 91.90% | Gap66.3 behind | Run by Vibe Code Bench | Shown only |
| SWE-bench (Vals)SWE-bench, Vals AI run | 73.4% | Best verified: Claude Opus 5 · 97.0% | Gap23.6 behind | Independent run: Vals AI | Shown only |
Agentic13 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| MCP Atlas | 48.2% | Best verified: Muse Spark Open · 89.2% | Gap41 behind | Reported by Alibaba | Counts5% ref. weight |
| Terminal-Bench 2.1 (Vals)Terminal-Bench 2.1, Vals AI run | 53.2% | Best verified: Claude Opus 5.5 · 87.6% | Gap34.4 behind | Independent run: Vals AI | Counts4% ref. weight |
| Toolathlon | 39.8% | Best verified: Muse Spark 1.1 · 75.6% | Gap35.8 behind | Reported by Alibaba | Counts3% ref. weight |
| τ³-bench resultsτ³-Bench Tool-Agent-User Evaluation | 70.7% | Best verified: Mercury 2.5 · 96.0% | Gap25.3 behind | Reported by Alibaba | Counts2% ref. weight |
| Terminal-Bench 2.0 | 61.6% | Best verified: GPT-5.5 · 82% | Gap20.4 behind | Reported by Alibaba | Shown only |
| Claw-Eval | 58.8% | Best verified: Ornith-1.5-397B · 81.4% | Gap22.6 behind | Run by Claw-Eval | Shown only |
| QwenClawBench | 57.2% | Best verified: Qwen3.7 Max · 64.3% | Gap7.1 behind | Reported by Alibaba | Shown only |
| VITA-Bench | 44.3% | Best verified: Qwen3.7 Max · 47.9% | Gap3.6 behind | Reported by Alibaba | Shown only |
| DeepPlanning | 41.5% | Best verified: Qwen3.7 Plus · 62.3% | Gap20.8 behind | Reported by Alibaba | Shown only |
| MCP-Tasks | 74.1% | Best verified: Qwen3.5 397B · 74.2% | Gap0.1 behind | Reported by Alibaba | Shown only |
| WideResearch | 74.3% | Best verified: Hy4 preview · 83.9% | Gap9.6 behind | Reported by Alibaba | Shown only |
| Gert LabsGert Labs Composite Game Benchmark | 50.60% | Best verified: Claude Opus 4.8 · 72.97% | Gap22.4 behind | Run by Gert Labs | Shown only |
| ResearchClawBench | 18.0% | Best verified: Claude Opus 4.8 · 21.1% | Gap3.1 behind | Run by ResearchClawBench | Shown only |
Reasoning2 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| LongBench v2 | 62% | Best verified: Inkling 2 Small · 70.6% | Gap8.6 behind | Reported by Alibaba | Counts5% ref. weight |
| AI-Needle | 68.3% | Best verified: Qwen3.5 397B · 68.7% | Gap0.4 behind | Reported by Alibaba | Shown only |
Multimodal7 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| MMMU-ProMassive Multi-discipline Multimodal Understanding Pro | 78.8% | Best verified: GPT-6.1 Terra · 85.5% | Gap6.7 behind | Reported by Alibaba | Counts30% ref. weight |
| CharXivCharXiv Reasoning | 81.5% | Best verified: Qwen3.8 Max · 93.5% | Gap12 behind | Reported by Alibaba | Counts17% ref. weight |
| ScreenSpot Pro | 68.2% | Best verified: GPT-6 Astra · 92.7% | Gap24.5 behind | Reported by Alibaba | Counts10% ref. weight |
| MMMUMassive Multi-discipline Multimodal Understanding | 86.0% | Best verified: Qwen3.5 397B · 85.0% | Gap1 behind | Carried from an upstream page | Shown only |
| MathVision | 88.0% | Best verified: Qwen3.8 Max · 95.2% | Gap7.2 behind | Reported by Alibaba | Shown only |
| VideoMMMU | 84.0% | Best verified: Qwen3.8 Max · 88.7% | Gap4.7 behind | Reported by Alibaba | Shown only |
| V* | 96.9% | Best verified: Kimi K2.6 · 96.9% | GapHighest listed | Reported by Alibaba | Shown only |
Knowledge8 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| HLEHumanity's Last Exam | 28.8% | Best verified: Claude Fable 5.2 · 74.2% | Gap45.4 behind | Reported by Alibaba | Counts44% ref. weight |
| MMLU-ProMassive Multitask Language Understanding Professional | 88.5% | Best verified: Qwen3.7 Max · 89.6% | Gap1.1 behind | Reported by Alibaba | Counts6% ref. weight |
| MMLU-Pro (Vals)MMLU-Pro, Vals AI run | 87.7% | Best verified: Claude Fable 5.1 · 92.4% | Gap4.7 behind | Independent run: Vals AI | Counts6% ref. weight |
| GPQAGraduate-Level Google-Proof Q&A | 90.4% | Best verified: GPT-6 Astra · 96% | Gap5.6 behind | Reported by Alibaba | Counts3% ref. weight |
| SuperGPQASuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines | 71.6% | Best verified: Qwen 3.6 Max (preview) · 73.9% | Gap2.3 behind | Reported by Alibaba | Counts2% ref. weight |
| GPQA Diamond (Vals)GPQA Diamond, Vals AI run | 87.4% | Best verified: Gemini 3.1 Pro · 95.5% | Gap8.1 behind | Independent run: Vals AI | Counts2% ref. weight |
| MMLU-Redux | 94.5% | Best verified: Qwen3.7 Max · 95% | Gap0.5 behind | Reported by Alibaba | Shown only |
| C-Eval | 93.3% | Best verified: Qwen3.6 Plus · 93.3% | GapHighest listed | Reported by Alibaba | Shown only |
Multilingual2 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| MMLU-ProX | 84.7% | Best verified: Qwen3.7 Max · 87% | Gap2.3 behind | Reported by Alibaba | CountsWeighted 100% |
| NOVA-63 | 57.9% | Best verified: Qwen3.5 397B · 59.1% | Gap1.2 behind | Reported by Alibaba | Shown only |
Inst. Following2 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| IFBenchInstruction Following Benchmark | 75.8% | Best verified: Flint · 89.2% | Gap13.4 behind | Reported by Alibaba | CountsWeighted 70% |
| IFEvalInstruction-Following Eval | 94.3% | Best verified: LFM2.5-24B-A2B · 96.8% | Gap2.5 behind | Reported by Alibaba | Shown only |
Math6 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3)FrontierMath v2 Tiers 1-3 | 38.246% | Best verified: Claude Fable 5.2 · 95.088% | Gap56.8 behind | Run by FrontierMath v2 (Tiers 1-3) | CountsWeighted 30% |
| AIME26AIME 2026 | 95.3% | Best verified: GLM-5.2 · 99.2% | Gap3.9 behind | Reported by Alibaba | CountsWeighted 25% |
| HMMT Feb 2026Harvard-MIT Mathematics Tournament February 2026 | 87.8% | Best verified: Qwen3.7 Max · 97.1% | Gap9.3 behind | Reported by Alibaba | CountsWeighted 25% |
| HMMT Feb 2025Harvard-MIT Mathematics Tournament February 2025 | 96.7% | Best verified: GLM-4.7 · 97.1% | Gap0.4 behind | Reported by Alibaba | Shown only |
| HMMT Nov 2025Harvard-MIT Mathematics Tournament November 2025 | 94.6% | Best verified: Qwen3.6 Plus · 94.6% | GapHighest listed | Reported by Alibaba | Shown only |
| MMAnswerBench | 83.8% | Best verified: GLM-5.2 · 91.0% | Gap7.2 behind | Reported by Alibaba | Shown only |
External signals3 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| NYT ConnectionsNYT Connections LLM Benchmark (extended version) | 60.3% | Best verified: Gemini 4 Carbon · 99.3% | Gap39 behind | Run by NYT Connections | Shown only |
| Chess PuzzlesChess Puzzles (Epoch AI) | 16.0% | Best verified: Claude Fable 5.2 · 79.0% | Gap63 behind | Run by Chess Puzzles | Shown only |
| Mystery Game PuzzlesMystery Game Puzzles (Epoch AI) | 12.0% | Best verified: Claude Fable 5.2 · 90.0% | Gap78 behind | Run by Mystery Game Puzzles | Shown only |
Outlined bars are lab-reported or carried from an upstream page. Filled bars are benchmark-run or independent. Bars run 0–100; the dark tick marks the best source-verified value.
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 1M
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- text, image, videoQwen Cloud model page for qwen3.6-plus
- Output modalities
- textQwen Cloud model page for qwen3.6-plus
- Parameters
- Not disclosed by the provider
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Superseded
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
Qwen3.6 Plus ranks #76 of 215 on the public leaderboard with a score of 53.41/100. Its source-verified position is #44 of 81.
Qwen3.6 Plus is a proprietary model with a 1M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Official first-party benchmark snapshot from Qwen's April 2, 2026 Qwen3.6 launch post, plus public release metadata for the hosted Qwen3.6 Plus model.
52 of 919 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Multilingual at #4, while its lowest eligible position is Reasoning at #98. a well-rounded choice across a range of tasks.
Last updated November 13, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Where to run Qwen3.6 Plus by API
2 hosts publish a per-token price for it. OpenRouter has the lowest output rate, $1.95 per million tokens. Prices read from each host’s own pages on November 11, 2026.
| Host | Input /1M | Output /1M | Cached /1M | Context |
|---|---|---|---|---|
| OpenRouter | $0.33 | $1.95 | — | 1M |
| Together AI | $0.50 | $3.00 | — | 1M |
Questions
How does Qwen3.6 Plus perform overall in AI benchmarks?
Qwen3.6 Plus ranks #76 out of 215 models on the public BenchAlign leaderboard, with a score of 53.41/100. Its evidence status is Supported, and this profile shows 52 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Qwen3.6 Plus good for knowledge and understanding?
Qwen3.6 Plus ranks #66 out of 180 eligible models for knowledge and understanding, with a public category score of 53.1/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Qwen3.6 Plus good for coding and programming?
Qwen3.6 Plus ranks #72 out of 162 eligible models for coding and programming, with a public category score of 39.8/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Qwen3.6 Plus good for mathematics?
Qwen3.6 Plus ranks #6 out of 12 eligible models for mathematics, with a public category score of 62.3/100. That places it in the current top ten for this category. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Qwen3.6 Plus good for reasoning and logic?
Qwen3.6 Plus ranks #98 out of 160 eligible models for reasoning and logic, with a public category score of 35.6/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Qwen3.6 Plus good for agentic tool use and computer tasks?
Qwen3.6 Plus ranks #87 out of 135 eligible models for agentic tool use and computer tasks, with a public category score of 34.3/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Qwen3.6 Plus good for multimodal and grounded tasks?
Qwen3.6 Plus ranks #46 out of 67 eligible models for multimodal and grounded tasks, with a public category score of 55.2/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Qwen3.6 Plus good for instruction following?
Qwen3.6 Plus ranks #50 out of 157 eligible models for instruction following, with a public category score of 85.8/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Qwen3.6 Plus good for multilingual tasks?
Qwen3.6 Plus ranks #4 out of 17 eligible models for multilingual tasks, with a public category score of 93.8/100. That places it in the current top ten for this category. Check the underlying rows before treating the aggregate as a workload guarantee.
Does Qwen3.6 Plus have full benchmark coverage on BenchLM?
No. Qwen3.6 Plus currently has 68 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Qwen3.6 Plus?
Qwen3.6 Plus has a reported context window of 1M in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.