Models · Qwen (Alibaba) · Out sinceReleased 2 Apr 2026
Qwen3.6 Plus
Qwen3.6 Plus is made by Qwen (Alibaba). We don't have enough test results yet to rank it. It's cheap to use.
Official list price not re-verified (OpenRouter: $0.325/$1.95). Context/max output from OpenRouter.
- —
- —
- —
- Cheap$0.33 / $1.95
- $0.73
- 1M
- 66K
- 22 (3 independent3 indep.)
- 2 Apr 2026
- Qwen (Alibaba)
- text, image, video
Scores are out of 100 for each area, compared with every model we track; “#” is its rank. Context is how much text it can read at once (1M is roughly 700,000 words). Blended price mixes the cost of what you send and what it writes back.
OpenRouter is a service that gives access to many AI models in one place. This model is listed there as qwen/qwen3.6-plus.
Route it as qwen/qwen3.6-plus at $0.33 in / $1.95 out per 1M tokens, 1M context. Listed since 2 Apr 2026.
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Every test result
Every result
All the numbers,with where they came from.
Every result we've found for this model, with who measured it and a link to where we read it.
All raw rows (vendor and independent kept separate), with setting label, source, date, harness and notes.
| NotesNotes | ||||||
|---|---|---|---|---|---|---|
| AIME 2026 | 95.3% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | — | Full AIME 2026 I & II |
| GPQA Diamond | 90.4% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | — | |
| HMMT February 2026 | 87.8% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | — | HMMT Feb 26 |
| Humanity's Last Exam | 28.8% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | — | |
| Humanity's Last Exam (with tools) | 50.6% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | — | |
| IMO-AnswerBench | 83.8% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | — | |
| LiveCodeBench | 86.0% | Default | Independent testIndependentVals.ai ↗ | 1 Sep 2026 | — | ±0.977 stderr; $0.078/test |
| LiveCodeBench | 87.1% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | — | LiveCodeBench v6 |
| LLM Creative Story-Writing Benchmark (Lech Mazur) | -2.3 | DefaultQwen 3.6 Plus | Independent testIndependentLech Mazur (LLM Creative Story-Writing Benchmark) ↗ | 28 Sep 2026 | — | rank 48/56; Thurstone comparison score (centered at 0); est. win chance 19%; 95% bootstrap -2.423 to -2.101 |
| MCP Atlas | 74.1% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | — | Public set |
| MCPMark | 48.2% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | — | |
| MMLU-Pro | 88.5% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | — | |
| MMMLU | 89.5% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | — | |
| NL2Repo-Bench | 37.9% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | Claude Code | |
| SimpleQA Verified | 44.1% | Defaultqwen3.6-plus | Independent testIndependentEpoch AI ↗ | 27 Aug 2026 | — | Epoch-run (no tools); ±1.57 stderr |
| SkillsBench | 45.7% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | OpenCode | Avg5, 78-task subset |
| SWE-bench Multilingual | 73.8% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | Internal scaffold (bash + file-edit) | |
| SWE-Bench Pro (public, v1) | 56.6% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | Internal scaffold (bash + file-edit) | Qwen-corrected ('refined') SWE-bench Pro |
| SWE-bench Verified | 78.8% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | Internal scaffold (bash + file-edit) | 200K ctx |
| tau3-bench | 70.7% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | — | |
| Terminal-Bench 2.0 | 61.6% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | Terminus 2 (Harbor) | 3h timeout, avg of 5 runs |
| Toolathlon | 39.8% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | 2 Apr 2026 | — | Reported as 'Tool Decathlon' |