Qwen3.6 27B vs Qwen3.6 Plus
Wins 0 of 8 areas
—
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Qwen3.6 Plus is the stronger all-rounder.
Scores updated · 52 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- CodingWriting and fixing software17Qwen3.6 Plus7 of 9 tests · 1 tie
- MathCompetition and research-level math05Qwen3.6 Plus5 of 5 tests
- ReasoningHard problems that need careful thinking04Qwen3.6 Plus4 of 4 tests
- Images and chartsUnderstanding pictures, charts and video04Qwen3.6 Plus4 of 4 tests
- FactsGetting facts right instead of making them up02Qwen3.6 Plus2 of 2 tests
- Following instructionsDoing exactly what it is asked02Qwen3.6 Plus2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01Qwen3.6 Plus1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01Qwen3.6 Plus1 of 1 test
Long documents rests on a single test.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Qwen3.6 Plus costs 17% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Qwen3.6 Plus pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+14.7points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+9.1points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+7.6points ahead
Where Qwen3.6 27B pulls ahead
- Code for real scientific research problemsSciCode+2.1points ahead
Every test, side by side
All 52 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.6 Plus
- Terminal-Bench HardQwen3.6 Plus by 9.134.843.9+9.1
- LiveBench · CodingQwen3.6 Plus by 6.471.878.2+6.4
- LiveCodeBench v6Qwen3.6 Plus by 3.283.987.1+3.2
- SWE-bench ProQwen3.6 Plus by 3.153.556.6+3.1
- SWE-bench MultilingualQwen3.6 Plus by 2.571.373.8+2.5
- LiveBench · Agentic CodingQwen3.6 Plus by 2.139.341.4+2.1
- SciCodeQwen3.6 27B by 2.142.840.7+2.1
- SWE-bench VerifiedQwen3.6 Plus by 1.677.278.8+1.6
- Terminal-Bench 2.1tie60.761.4tie
AgentsQwen3.6 Plus
- τ-Bench V3 · BankingQwen3.6 Plus by 4.116.720.8+4.1
- GDPValtie24.424.7tie
ReasoningQwen3.6 Plus
- LiveBench · ReasoningQwen3.6 Plus by 5.570.375.8+5.5
- Humanity's Last ExamQwen3.6 Plus by 4.723.127.8+4.7
- GPQA DiamondQwen3.6 Plus by 484.288.2+4
- CritPtQwen3.6 Plus by 1.81.12.9+1.8
FactsQwen3.6 Plus
- AA-Omniscience · Non-hallucinationQwen3.6 Plus by 14.750.765.4+14.7
- AA-Omniscience · AccuracyQwen3.6 Plus by 6.819.626.4+6.8
Images and chartsQwen3.6 Plus
- MMMU-ProQwen3.6 Plus by 3.474.678+3.4
- CharXiv (RQ)Qwen3.6 Plus by 3.178.481.5+3.1
- MMMUQwen3.6 Plus by 3.182.986+3.1
- MMStarQwen3.6 Plus by 1.981.483.3+1.9
MathQwen3.6 Plus
- LiveBench · MathematicsQwen3.6 Plus by 3.879.983.7+3.8
- HMMT Feb. 2026Qwen3.6 Plus by 3.584.387.8+3.5
- FrontierMath Tiers 1-3 (v2)Qwen3.6 Plus by 3.235.138.3+3.2
- IMOAnswerBenchQwen3.6 Plus by 380.883.8+3
- AIME 2026Qwen3.6 Plus by 1.294.195.3+1.2
Following instructionsQwen3.6 Plus
- IFBenchQwen3.6 Plus by 7.667.675.2+7.6
- LiveBench · Instruction FollowingQwen3.6 Plus by 5.153.258.3+5.1
Other results23 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- AA-OmniscienceQwen3.6 Plus by 20.9-200.9+20.9
- livebench_languageQwen3.6 Plus by 11.763.375+11.7
- SimpleVQAQwen3.6 Plus by 11.256.167.3+11.2
- AA Agentic IndexQwen3.6 Plus by 8.920.129+8.9
- AA IntelligenceQwen3.6 Plus by 5.621.427+5.6
- SuperGPQAQwen3.6 Plus by 5.66671.6+5.6
- HMMT 2025Qwen3.6 Plus by 3.990.794.6+3.9
- HMMT Nov. 2025Qwen3.6 Plus by 3.990.794.6+3.9
- τ²-Bench Telecom (AA run)Qwen3.6 Plus by 3.594.297.7+3.5
- ERQAQwen3.6 Plus by 3.262.565.7+3.2
- DynaMathQwen3.6 Plus by 2.485.688+2.4
- MMLU-ProQwen3.6 Plus by 2.386.288.5+2.3
- Terminal-Bench 2.0Qwen3.6 Plus by 2.359.361.6+2.3
- CC-OCRQwen3.6 Plus by 2.281.283.4+2.2
- C-EvalQwen3.6 Plus by 1.991.493.3+1.9
- Claw Eval (pass@3)Qwen3.6 27B by 1.960.658.7+1.9
- NL2RepoQwen3.6 Plus by 1.736.237.9+1.7
- RealWorldQAQwen3.6 Plus by 1.384.185.4+1.3
- MMLU-ReduxQwen3.6 Plus by 193.594.5+1
- Artificial Analysis Coding Indextie53.754.5tie
- livebench_data_analysistie70.469.9tie
- VideoMMMUtie84.484tie
- MLVUtie86.686.7tie
Questions people ask
Which is better, Qwen3.6 27B or Qwen3.6 Plus?
Qwen3.6 Plus wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. Qwen3.6 27B wins none.
Which is better for coding?
Qwen3.6 Plus. It wins 7 of the 9 coding tests both models report; Qwen3.6 27B wins 1, and 1 is a tie.
Which is cheaper?
Qwen3.6 27B costs $0.60 per million input tokens and $3.60 per million output tokens; Qwen3.6 Plus costs $0.50 and $3.00. That makes Qwen3.6 Plus about 17% cheaper for the same work.
How do you compare the two?
We use the 52 benchmark tests both models have published scores on. The verdict counts the 29 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 23 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.