Qwen3.5 122B A10B vs Qwen3.6 Plus
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents
Qwen3.6 Plus is the stronger all-rounder.
Scores updated · 54 tests both models report · How we compare
Where each one wins
Tests won in each of the seven areas where both have results. 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 software08Qwen3.6 Plus8 of 8 tests
- Images and chartsUnderstanding pictures, charts and video03Qwen3.6 Plus3 of 4 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own03Qwen3.6 Plus3 of 3 tests
- ReasoningHard problems that need careful thinking03Qwen3.6 Plus3 of 3 tests
- FactsGetting facts right instead of making them up02Qwen3.6 Plus2 of 2 tests
- Long documentsFinding answers in very long texts02Qwen3.6 Plus2 of 2 tests
- Following instructionsDoing exactly what it is asked00Even0 each · 1 tie
Following instructions 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 3% 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+52.5points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+13.8points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+12.8points ahead
Where Qwen3.5 122B A10B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 54 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.6 Plus
- Terminal-Bench 2.1Qwen3.6 Plus by 13.847.661.4+13.8
- Terminal-Bench HardQwen3.6 Plus by 12.831.143.9+12.8
- SWE-bench MultilingualQwen3.6 Plus by 11.86273.8+11.8
- SWE-bench ProQwen3.6 Plus by 11.744.956.6+11.7
- LMArena · WebDevQwen3.6 Plus by 101 rating points13601461+101 rating
- LiveCodeBench v6Qwen3.6 Plus by 8.278.987.1+8.2
- SWE-bench VerifiedQwen3.6 Plus by 6.87278.8+6.8
- SciCodeQwen3.6 Plus by 139.740.7+1
AgentsQwen3.6 Plus
- GDPValQwen3.6 Plus by 8.815.724.5+8.8
- τ-Bench V3 · BankingQwen3.6 Plus by 5.515.320.8+5.5
- OSWorld-VerifiedQwen3.6 Plus by 4.55862.5+4.5
ReasoningQwen3.6 Plus
- Humanity's Last ExamQwen3.6 Plus by 2.625.227.8+2.6
- GPQA DiamondQwen3.6 Plus by 2.585.788.2+2.5
- CritPtQwen3.6 Plus by 2.30.62.9+2.3
FactsQwen3.6 Plus
- AA-Omniscience · Non-hallucinationQwen3.6 Plus by 52.512.965.4+52.5
- AA-Omniscience · AccuracyQwen3.6 Plus by 224.426.4+2
Images and chartsQwen3.6 Plus
- CharXiv (RQ)Qwen3.6 Plus by 4.377.281.5+4.3
- MMMU-ProQwen3.6 Plus by 37578+3
- MMMUQwen3.6 Plus by 2.183.986+2.1
- MMStartie82.983.3tie
Long documentsQwen3.6 Plus
- AA-LCRQwen3.6 Plus by 276.378.3+2
- LongBench v2Qwen3.6 Plus by 1.860.262+1.8
Other results31 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 42.4-41.50.9+42.4
- AA Agentic IndexQwen3.6 Plus by 19.49.629+19.4
- DeepPlanningQwen3.6 Plus by 17.424.141.5+17.4
- WideSearchQwen3.6 Plus by 13.860.574.3+13.8
- Terminal-Bench 2.0Qwen3.6 Plus by 12.249.461.6+12.2
- AA IntelligenceQwen3.6 Plus by 11.415.627+11.4
- VITA-BenchQwen3.6 Plus by 10.733.644.3+10.7
- Artificial Analysis Coding IndexQwen3.6 Plus by 8.845.754.5+8.8
- WMT24++Qwen3.6 Plus by 678.384.3+6
- SimpleVQAQwen3.6 Plus by 5.661.767.3+5.6
- SuperGPQAQwen3.6 Plus by 4.567.171.6+4.5
- HMMT 2025Qwen3.6 Plus by 4.390.394.6+4.3
- τ²-Bench Telecom (AA run)Qwen3.6 Plus by 4.193.697.7+4.1
- ERQAQwen3.6 Plus by 3.76265.7+3.7
- MMlongBench DocQwen3.6 Plus by 35962+3
- MMMLUQwen3.6 Plus by 2.886.789.5+2.8
- MMLU-ProXQwen3.6 Plus by 2.582.284.7+2.5
- IncludeQwen3.6 Plus by 2.382.885.1+2.3
- ScreenSpot-Pro (No tools)Qwen3.5 122B A10B by 2.270.468.2+2.2
- DynaMathQwen3.6 Plus by 2.185.988+2.1
- VideoMMMUQwen3.6 Plus by 28284+2
- MATH-VisionQwen3.6 Plus by 1.886.288+1.8
- MMLU-ProQwen3.6 Plus by 1.886.788.5+1.8
- CC-OCRQwen3.6 Plus by 1.681.883.4+1.6
- C-EvalQwen3.6 Plus by 1.491.993.3+1.4
- OmniDocBench 1.5Qwen3.6 Plus by 1.489.891.2+1.4
- AI2DQwen3.6 Plus by 1.193.394.4+1.1
- IFEvaltie93.494.3tie
- MLVUtie87.386.7tie
- MMLU-Reduxtie9494.5tie
- RealWorldQAtie85.185.4tie
Questions people ask
Which is better, Qwen3.5 122B A10B or Qwen3.6 Plus?
Qwen3.6 Plus wins six of the seven areas where both have results: coding, agents, reasoning, facts, images and charts and long documents. Qwen3.5 122B A10B wins none. They are level on following instructions.
Which is better for coding?
Qwen3.6 Plus. It wins 8 of the 8 coding tests both models report; Qwen3.5 122B A10B wins none.
Which is cheaper?
Qwen3.5 122B A10B costs $0.40 per million input tokens and $3.20 per million output tokens; Qwen3.6 Plus costs $0.50 and $3.00. That makes Qwen3.6 Plus about 3% cheaper for the same work.
How do you compare the two?
We use the 54 benchmark tests both models have published scores on. The verdict counts the 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 31 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.