Claude Sonnet 4.5 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 · 45 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 8 tests
- ReasoningHard problems that need careful thinking03Qwen3.6 Plus3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video03Qwen3.6 Plus3 of 3 tests
- AgentsCarrying out multi-step tasks on its own13Qwen3.6 Plus3 of 4 tests
- MathCompetition and research-level math02Qwen3.6 Plus2 of 2 tests
- FactsGetting facts right instead of making them up12Qwen3.6 Plus2 of 3 tests
- Long documentsFinding answers in very long texts01Qwen3.6 Plus1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked01Qwen3.6 Plus1 of 1 test
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 81% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.6 Plus pulls ahead
- Multi-step tasks using many real software toolsMCP Atlas+30.3points ahead
- Recent programming contest problemsLiveCodeBench v6+23.1points ahead
- Olympiad math problems with short answersIMOAnswerBench+17.9points ahead
Where Claude Sonnet 4.5 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+6.5points ahead
- Code for real scientific research problemsSciCode+5points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+3.7points ahead
Every test, side by side
All 45 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.6 Plus
- LiveCodeBench v6Qwen3.6 Plus by 23.16487.1+23.1
- SWE-bench ProQwen3.6 Plus by 1343.656.6+13
- Terminal-Bench HardQwen3.6 Plus by 8.335.643.9+8.3
- SWE-bench MultilingualQwen3.6 Plus by 6.86773.8+6.8
- LMArena · WebDevQwen3.6 Plus by 67 rating points13941461+67 rating
- Terminal-Bench 2.1Qwen3.6 Plus by 5.655.861.4+5.6
- SciCodeClaude Sonnet 4.5 by 545.740.7+5
- SWE-bench VerifiedQwen3.6 Plus by 1.677.278.8+1.6
AgentsQwen3.6 Plus
- MCP AtlasQwen3.6 Plus by 30.343.874.1+30.3
- GDPValQwen3.6 Plus by 4.220.524.7+4.2
- τ-Bench V3 · BankingClaude Sonnet 4.5 by 3.724.520.8+3.7
- OSWorld-VerifiedQwen3.6 Plus by 1.161.462.5+1.1
ReasoningQwen3.6 Plus
- Humanity's Last ExamQwen3.6 Plus by 1017.827.8+10
- GPQA DiamondQwen3.6 Plus by 4.883.488.2+4.8
- CritPtQwen3.6 Plus by 1.81.12.9+1.8
FactsQwen3.6 Plus
- AA-Omniscience · Non-hallucinationQwen3.6 Plus by 14.550.965.4+14.5
- SimpleQA VerifiedQwen3.6 Plus by 13.430.744.1+13.4
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 6.532.926.4+6.5
Images and chartsQwen3.6 Plus
- CharXiv (RQ)Qwen3.6 Plus by 14.367.281.5+14.3
- MMMU-ProQwen3.6 Plus by 9.368.778+9.3
- MMMUQwen3.6 Plus by 6.479.686+6.4
MathQwen3.6 Plus
- IMOAnswerBenchQwen3.6 Plus by 17.965.983.8+17.9
- FrontierMath Tiers 1-3 (v2)Qwen3.6 Plus by 14.423.938.3+14.4
Long documentsQwen3.6 Plus
- AA-LCRQwen3.6 Plus by 672.378.3+6
- LongBench v2tie61.862tie
Following instructionsQwen3.6 Plus
- IFBenchQwen3.6 Plus by 17.957.375.2+17.9
Other results19 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.
- HMMT 2025Qwen3.6 Plus by 2074.694.6+20
- τ²-Bench Telecom (AA run)Qwen3.6 Plus by 19.678.197.7+19.6
- HLE (with tools)Qwen3.6 Plus by 18.63250.6+18.6
- CC-OCRQwen3.6 Plus by 15.368.183.4+15.3
- RealWorldQAQwen3.6 Plus by 15.170.385.4+15.1
- HMMT Nov. 2025Qwen3.6 Plus by 12.981.794.6+12.9
- Terminal-Bench 2.0Qwen3.6 Plus by 11.65061.6+11.6
- AA Agentic IndexQwen3.6 Plus by 11.517.529+11.5
- SimpleVQAQwen3.6 Plus by 9.757.667.3+9.7
- AI2DQwen3.6 Plus by 7.48794.4+7.4
- AA IntelligenceQwen3.6 Plus by 6.320.727+6.3
- OmniDocBench 1.5Qwen3.6 Plus by 5.485.891.2+5.4
- frontiermath_tier_4_v1Qwen3.6 Plus by 4.14.28.3+4.1
- Artificial Analysis Coding IndexQwen3.6 Plus by 2.452.154.5+2.4
- ToolathlonClaude Sonnet 4.5 by 1.24139.8+1.2
- MMLU-ReduxClaude Sonnet 4.5 by 1.195.694.5+1.1
- AA-OmniscienceQwen3.6 Plus by 1-0.10.9+1
- MMLU-ProQwen3.6 Plus by 187.588.5+1
- MMMLUtie89.189.5tie
Questions people ask
Which is better, Claude Sonnet 4.5 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. Claude Sonnet 4.5 wins none.
Which is better for coding?
Qwen3.6 Plus. It wins 7 of the 8 coding tests both models report; Claude Sonnet 4.5 wins 1.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; Qwen3.6 Plus costs $0.50 and $3.00. That makes Qwen3.6 Plus about 81% cheaper for the same work.
How do you compare the two?
We use the 45 benchmark tests both models have published scores on. The verdict counts the 26 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 19 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.