AlibabaQwen3.6 Plus
Best configuration ranks #111 of 610 on the BenchLeader Index at 59.0 ±4.3. Last measured 8 Sept 2026. Released 31 Mar 2026.
- Blended price
- $1.13/M
- $0.500 in · $3.00 out
- Output speed
- 56 tok/s
- First answer
- 101 s
- first token 0.75 s
- Context
- 1M
- Overall index59
- Reasoning64
- Coding53
- Agents & tools57
- Maths57
- Knowledge59
- Instruction following73
- Human preference64
- Multimodal63
- Long context66
- Composite48
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Default” means the publisher did not say which setting was used.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| no reasoning | – | – | 56 tok/s | 101 s | $0.0011 | Maths 45 |
| defaultbest | 59.0 | #111 | 56 tok/s | 101 s | $0.0011 | Agents & tools 57 · Coding 53 · Composite 48 · Human preference 64 · Instruction following 73 · Knowledge 59 · Long context 66 · Maths 57 · Multimodal 63 · Reasoning 64 |
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| GPQA Diamond | – | 88.4%#49 | Epoch AI Benchmarking Hub | |
| LMArena Hard Prompts | – | 1468#71 | LMArena | |
| LiveBench Reasoningnot in index | – | 75.8%#46 | LiveBench | |
| GPQA Diamond (AA)not in index | – | 88.2%#90 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | – | 27.9%#123 | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | – | 87.4%#37 | Vals AI |
Coding
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| SWE-bench Verified (Epoch) | – | 57.9%#30 | Epoch AI Benchmarking Hub | |
| SciCode | – | 40.7%#103 | SciCode | |
| LMArena Coding | – | 1495#71 | LMArena | |
| LMArena WebDev | – | 1460#51 | LMArena | |
| LiveBench Codingnot in index | – | 78.2%#22 | LiveBench | |
| LiveCodeBench | – | 86.0%#24 | Vals AI | |
| SWE-bench (Vals)not in index | – | 73.4%#50 | Vals AI |
Agents & tools
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| LiveBench Agentic Codingnot in index | – | 41.4%#47 | LiveBench | |
| Terminal-Bench Hard | – | 43.9%#35 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | – | 97.7%#9 | Artificial Analysis | |
| Terminal-Bench 2.1 (Vals) | – | 53.2%#45 | Vals AI |
Maths
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| FrontierMath Tiers 1–3 | 32.3%#57 | 38.3%#48 | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | – | 93.3%#44 | Epoch AI Benchmarking Hub | |
| LiveBench Mathematicsnot in index | – | 83.7%#44 | LiveBench | |
| AIME (Vals) | – | 94.6%#13 | Vals AI |
Knowledge
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| SimpleQA Verified | – | 44.1%#33 | Epoch AI Benchmarking Hub | |
| LiveBench Data Analysisnot in index | – | 69.9%#40 | LiveBench | |
| AA-Omniscience | – | 0.9#87 | Artificial Analysis | |
| MMLU-Pro | – | 87.7%#24 | Vals AI | |
| LegalBench | – | 84.2%#33 | Vals AI | |
| CorpFin | – | 61.9%#50 | Vals AI | |
| TaxEval | – | 74.7%#30 | Vals AI |
Instruction following
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| LiveBench Languagenot in index | – | 75.0%#38 | LiveBench | |
| IFBench | – | 75.2%#34 | Artificial Analysis |
Human preference
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| LMArena Text | – | 1444#74 | LMArena |
Multimodal
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| MMMU-Pro | – | 78.0%#56 | Artificial Analysis |
Long context
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| AA-LCR | – | 78.3%#77 | Artificial Analysis |
Composite
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| Epoch Capabilities Indexnot in index | – | 147.7#52 | Epoch AI Benchmarking Hub | |
| LiveBench | – | 68.9%#44 | LiveBench | |
| AA Intelligence Index | – | 27.0#101 | Artificial Analysis | |
| Vals Indexnot in index | – | 32.0#40 | Vals AI |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Alibaba Cloud Int. | 39 tok/s | 0.75 s | $0.325 | $1.95 | 1M | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.050 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0011 | $0.0010 | 1.8 min |
| Summarise a 30-page report | 12,000 / 600 | $0.0078 | $0.0038 | 1.9 min |
| Code edit | 6,000 / 1,500 | $0.0075 | $0.0055 | 2.1 min |
| Agentic coding session | 60,000 / 4,000 | $0.042 | $0.022 | 2.9 min |
| Structured extraction | 2,000 / 200 | $0.0016 | $0.0009 | 1.7 min |
See also
Data as of 9 Sept 2026. Compare these configurations.