Capability
64.8/100
field median 58.2
#35 of 218 ranked models
Superseded.Alibaba has newer models in this line:Qwen3.7 Plus
Qwen3.6 Plus
Released Apr 2, 2026 — see all recent releases
Decision reading
Qwen3.6 Plus scores 64.8 out of 100 and ranks #35 of 218. This profile shows 44 source-displayable benchmark rows; its strongest eligible category is Multilingual at #4. No comparable first-party API price is published in the catalog.
Data as of August 15, 2026 · How the score is built
Strongest published evidence
Multilingual ranks #4. A well-rounded choice across a range of tasks.
Validate before choosing
44 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Price
API rate not published
input median $1
No comparable first-party hosted token rate
Speed
56tok/s
field median 94 tok/s
First token 100.93 s
Context
1Mtokens
field median 200,000
Reported for this model; direct source link not stored
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
- Agentic15th percentile
- Coding54th percentile
- ReasoningNot eligible
- Knowledge21st percentile
- Math50th percentile
- Multilingual75th percentile
- Multimodal52nd percentile
- Instruction following56th percentile
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#111/130
- Coding#63/135
- ReasoningNot ranked
- Knowledge#45/57
- Math#4/7
- Multilingual#4/13
- Multimodal#16/32
- Inst. Following#18/40
Top decileTop quartileMid-fieldNot eligible
How 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.
- Agentic12/12 verified
- Coding6/6 verified
- Reasoning2/2 verified
- Knowledge6/6 verified
- Math7/7 verified
- Multilingual2/2 verified
- Multimodal6/7 verified
- Inst. Following2/2 verified
Verified sourceProvisionalNot measured
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
- Not sourced yet
- Output modalities
- Not sourced yet
- 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
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 #111 of 130Percentile 15thWeight 22%12 benchmarksVerified | 37.2 | #111 of 130 | 15th | 22% | 12 benchmarks | Verified |
| CodingRank #63 of 135Percentile 54thWeight 20%6 benchmarksVerified | 51.6 | #63 of 135 | 54th | 20% | 6 benchmarks | Verified |
| ReasoningRank Not rankedWeight 17%2 benchmarksVerified | 79.0 | Not ranked | Not available | 17% | 2 benchmarks | Verified |
| KnowledgeRank #45 of 57Percentile 21stWeight 12%6 benchmarksVerified | 58.6 | #45 of 57 | 21st | 12% | 6 benchmarks | Verified |
| MathRank #4 of 7Percentile 50thWeight 5%7 benchmarksVerified | 62.6 | #4 of 7 | 50th | 5% | 7 benchmarks | Verified |
| MultilingualRank #4 of 13Percentile 75thWeight 7%2 benchmarksVerified | 69.7 | #4 of 13 | 75th | 7% | 2 benchmarks | Verified |
| MultimodalRank #16 of 32Percentile 52ndWeight 12%7 benchmarksMixed sources | 66.2 | #16 of 32 | 52nd | 12% | 7 benchmarks | Mixed sources |
| Inst. FollowingRank #18 of 40Percentile 56thWeight 5%2 benchmarksVerified | 86.6 | #18 of 40 | 56th | 5% | 2 benchmarks | Verified |
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding6 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score78.8% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap17.2 behind | WeightWeighted 16% | Provider exact |
| SWE-bench Pro | Score56.6% | Versus best verified row Best verified: Claude Mythos 5 · 80.3% | Gap23.7 behind | WeightWeighted 10% | Provider exact |
| SWE Multilingual | Score73.8% | Versus best verified row Best verified: Claude Opus 5 · 89.5% | Gap15.7 behind | WeightDisplay only | Provider exact |
| LiveCodeBench v6 | Score87.1% | Versus best verified row Best verified: Sakana Fugu-Ultra · 93.2% | Gap6.1 behind | WeightDisplay only | Provider exact |
| Vibe Code BenchVibe Code Bench v1.1 | Score25.56% | Versus best verified row Best verified: Claude Opus 4.7 · 71.00% | Gap45.4 behind | WeightDisplay only | Benchmark exact |
| EEBenchEEBench V1 core corpus | Score12.7% | Versus best verified row Best verified: Grok 4.6 · 58.3% | Gap45.6 behind | WeightDisplay only | Benchmark exact |
Agentic12 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 | Score61.6% | Versus best verified row Best verified: GPT-5.6 Sol · 91.9% | Gap30.3 behind | WeightWeighted 38% | Provider exact |
| Claw-Eval | Score58.8% | Versus best verified row Best verified: Ornith-1.0-397B · 77.1% | Gap18.3 behind | WeightDisplay only | Benchmark exact |
| QwenClawBench | Score57.2% | Versus best verified row Best verified: Qwen3.7 Max · 64.3% | Gap7.1 behind | WeightDisplay only | Provider exact |
| τ³-bench resultsτ³-Bench Tool-Agent-User Evaluation | Score70.7% | Versus best verified row Best verified: Mistral Medium 3.5 128B · 91.4% | Gap20.7 behind | WeightDisplay only | Provider exact |
| VITA-Bench | Score44.3% | Versus best verified row Best verified: Qwen3.7 Max · 47.9% | Gap3.6 behind | WeightDisplay only | Provider exact |
| DeepPlanning | Score41.5% | Versus best verified row Best verified: Qwen3.7 Plus · 62.3% | Gap20.8 behind | WeightDisplay only | Provider exact |
| Toolathlon | Score39.8% | Versus best verified row Best verified: Muse Spark 1.1 · 75.6% | Gap35.8 behind | WeightDisplay only | Provider exact |
| MCP Atlas | Score48.2% | Versus best verified row Best verified: Muse Spark 1.1 · 88.1% | Gap39.9 behind | WeightDisplay only | Provider exact |
| MCP-Tasks | Score74.1% | Versus best verified row Best verified: Qwen3.5 397B · 74.2% | Gap0.1 behind | WeightDisplay only | Provider exact |
| WideResearch | Score74.3% | Versus best verified row Best verified: Qwen3.8 Max · 81.9% | Gap7.6 behind | WeightDisplay only | Provider exact |
| Gert LabsGert Labs Composite Game Benchmark | Score50.60% | Versus best verified row Best verified: Claude Opus 4.8 · 72.97% | Gap22.4 behind | WeightDisplay only | Benchmark exact |
| ResearchClawBench | Score18.0% | Versus best verified row Best verified: Claude Opus 4.8 · 21.1% | Gap3.1 behind | WeightDisplay only | Benchmark exact |
Reasoning2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| LongBench v2 | Score62% | Versus best verified row Best verified: Qwen3.8 Max · 66.3% | Gap4.3 behind | WeightWeighted 38% | Provider exact |
| AI-Needle | Score68.3% | Versus best verified row Best verified: Qwen3.5 397B · 68.7% | Gap0.4 behind | WeightDisplay only | Provider exact |
Knowledge6 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HLEHumanity's Last Exam | Score28.8% | Versus best verified row Best verified: Claude Opus 5 · 64.7% | Gap35.9 behind | WeightWeighted 45% | Provider exact |
| MMLU-ProMassive Multitask Language Understanding Professional | Score88.5% | Versus best verified row Best verified: Qwen3.7 Max · 89.6% | Gap1.1 behind | WeightWeighted 30% | Provider exact |
| GPQAGraduate-Level Google-Proof Q&A | Score90.4% | Versus best verified row Best verified: Sakana Fugu-Ultra · 95.5% | Gap5.1 behind | WeightWeighted 7% | Provider exact |
| SuperGPQASuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines | Score71.6% | Versus best verified row Best verified: Qwen 3.6 Max (preview) · 73.9% | Gap2.3 behind | WeightWeighted 7% | Provider exact |
| MMLU-Redux | Score94.5% | Versus best verified row Best verified: Qwen3.7 Max · 95% | Gap0.5 behind | WeightDisplay only | Provider exact |
| C-Eval | Score93.3% | Versus best verified row Best verified: Qwen3.6 Plus · 93.3% | GapBest verified | WeightDisplay only | Provider exact |
Math7 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3)FrontierMath v2 Tiers 1-3 | Score26.207% | Versus best verified row Best verified: GPT-5.6 Sol · 89.000% | Gap62.8 behind | WeightWeighted 30% | Benchmark exact |
| AIME26AIME 2026 | Score95.3% | Versus best verified row Best verified: GLM-5.2 · 99.2% | Gap3.9 behind | WeightWeighted 25% | Provider exact |
| HMMT Feb 2026Harvard-MIT Mathematics Tournament February 2026 | Score87.8% | Versus best verified row Best verified: Qwen3.7 Max · 97.1% | Gap9.3 behind | WeightWeighted 25% | Provider exact |
| FrontierMath v2 (Tier 4)FrontierMath v2 Tier 4 | Score8.333% | Versus best verified row Best verified: GPT-5.6 Sol · 83.000% | Gap74.7 behind | WeightWeighted 10% | Benchmark exact |
| HMMT Feb 2025Harvard-MIT Mathematics Tournament February 2025 | Score96.7% | Versus best verified row Best verified: Qwen3.6 Plus · 96.7% | GapBest verified | WeightDisplay only | Provider exact |
| HMMT Nov 2025Harvard-MIT Mathematics Tournament November 2025 | Score94.6% | Versus best verified row Best verified: Qwen3.6 Plus · 94.6% | GapBest verified | WeightDisplay only | Provider exact |
| MMAnswerBench | Score83.8% | Versus best verified row Best verified: GLM-5.2 · 91.0% | Gap7.2 behind | WeightDisplay only | Provider exact |
Multilingual2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMLU-ProX | Score84.7% | Versus best verified row Best verified: Qwen3.7 Max · 87% | Gap2.3 behind | WeightWeighted 100% | Provider exact |
| NOVA-63 | Score57.9% | Versus best verified row Best verified: Qwen3.5 397B · 59.1% | Gap1.2 behind | WeightDisplay only | Provider exact |
Multimodal7 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMMU-ProMassive Multi-discipline Multimodal Understanding Pro | Score78.8% | Versus best verified row Best verified: GPT-5.4 Pro · 94% | Gap15.2 behind | WeightWeighted 45% | Provider exact |
| CharXivCharXiv Reasoning | Score81.5% | Versus best verified row Best verified: Claude Mythos 5 · 93.5% | Gap12 behind | WeightWeighted 25% | Provider exact |
| MMMUMassive Multi-discipline Multimodal Understanding | Score86.0% | Versus best verified row Best verified: Qwen3.6-27B · 82.9% | Gap3.1 behind | WeightDisplay only | Reported |
| MathVision | Score88.0% | Versus best verified row Best verified: Qwen3.8 Max · 95.2% | Gap7.2 behind | WeightDisplay only | Provider exact |
| VideoMMMU | Score84.0% | Versus best verified row Best verified: Qwen3.8 Max · 88.7% | Gap4.7 behind | WeightDisplay only | Provider exact |
| ScreenSpot Pro | Score68.2% | Versus best verified row Best verified: Claude Opus 4.8 · 87.9% | Gap19.7 behind | WeightDisplay only | Provider exact |
| V* | Score96.9% | Versus best verified row Best verified: Kimi K2.6 · 96.9% | GapBest verified | WeightDisplay only | Provider exact |
Inst. Following2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| IFBenchInstruction Following Benchmark | Score75.8% | Versus best verified row Best verified: MAI-Thinking-1 · 85% | Gap9.2 behind | WeightWeighted 65% | Provider exact |
| IFEvalInstruction-Following Eval | Score94.3% | Versus best verified row Best verified: Qwen3.5-27B · 95% | Gap0.7 behind | WeightWeighted 35% | Provider exact |
Lineage
The sequence follows explicit supersedes links. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Apr 2, 2026 · you are here
Qwen3.6 PlusScore 64.8 · Price not listed
Jun 3, 2026
Qwen3.7 PlusScore 66.0 · Price not listed
Base entry
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 #35 of 218 on the public leaderboard with a score of 64.79/100. Its source-verified position is #31 of 104.
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.
44 of 437 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 Agentic at #111. a well-rounded choice across a range of tasks.
Radar
Full release historyQwen3.6 Plus release history
Qwen3.6 Plus released
Alibaba · Model release
Source confirmed
Frequently asked questions
How does Qwen3.6 Plus perform overall in AI benchmarks?
Qwen3.6 Plus ranks #35 out of 218 models on the public BenchAlign leaderboard, with a score of 64.79/100. Its evidence status is Supported, and this profile shows 44 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 #45 out of 57 eligible models for knowledge and understanding, with a public category score of 58.6/100. 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 coding and programming?
Qwen3.6 Plus ranks #63 out of 135 eligible models for coding and programming, with a public category score of 51.6/100. 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 mathematics?
Qwen3.6 Plus ranks #4 out of 7 eligible models for mathematics, with a public category score of 62.6/100. 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 has source-displayable benchmark coverage for reasoning and logic, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Qwen3.6 Plus good for agentic tool use and computer tasks?
Qwen3.6 Plus ranks #111 out of 130 eligible models for agentic tool use and computer tasks, with a public category score of 37.2/100. 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 multimodal and grounded tasks?
Qwen3.6 Plus ranks #16 out of 32 eligible models for multimodal and grounded tasks, with a public category score of 66.2/100. 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 #18 out of 40 eligible models for instruction following, with a public category score of 86.6/100. 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 multilingual tasks?
Qwen3.6 Plus ranks #4 out of 13 eligible models for multilingual tasks, with a public category score of 69.7/100. 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 61 source-displayable rows across 437 tracked benchmark slots. 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.
Last updated August 15, 2026. Runtime fields remain blank until a sourced snapshot exists.
Watch Qwen3.6 Plus in the weekly brief
Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.
Read a sample issueJoin 2,000+ readers.