Claude Sonnet 4.5 vs Qwen3.6 27B
Wins 1 of 8 areas
Facts
Wins 6 of 8 areas
Coding · Reasoning · Images and charts · Math · Long documents · Following instructions
Qwen3.6 27B is the stronger all-rounder.Claude Sonnet 4.5 is better at facts.
Scores updated · 37 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.
- Images and chartsUnderstanding pictures, charts and video04Qwen3.6 27B4 of 4 tests
- CodingWriting and fixing software14Qwen3.6 27B4 of 7 tests · 2 ties
- MathCompetition and research-level math02Qwen3.6 27B2 of 2 tests
- ReasoningHard problems that need careful thinking01Qwen3.6 27B1 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts01Qwen3.6 27B1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.6 27B1 of 1 test
- FactsGetting facts right instead of making them up10Claude Sonnet 4.51 of 2 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own11Even1 each · 1 tie
Long documents and following instructions rest on a single test each.
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 27B costs 77% 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 27B pulls ahead
- Recent programming contest problemsLiveCodeBench v6+19.9points ahead
- Olympiad math problems with short answersIMOAnswerBench+14.9points ahead
- Reasoning about charts from research papersCharXiv (RQ)+11.2points ahead
Where Claude Sonnet 4.5 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+13.3points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+7.8points ahead
- Code for real scientific research problemsSciCode+2.9points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.6 27B
- LiveCodeBench v6Qwen3.6 27B by 19.96483.9+19.9
- SWE-bench ProQwen3.6 27B by 9.943.653.5+9.9
- Terminal-Bench 2.1Qwen3.6 27B by 4.955.860.7+4.9
- SWE-bench MultilingualQwen3.6 27B by 4.36771.3+4.3
- SciCodeClaude Sonnet 4.5 by 2.945.742.8+2.9
- Terminal-Bench Hardtie35.634.8tie
- SWE-bench Verifiedtie77.277.2tie
AgentsEven
- τ-Bench V3 · BankingClaude Sonnet 4.5 by 7.824.516.7+7.8
- GDPValQwen3.6 27B by 3.920.524.4+3.9
- Terminal-Bench 4.0tie00tie
ReasoningQwen3.6 27B
- Humanity's Last ExamQwen3.6 27B by 5.317.823.1+5.3
- GPQA Diamondtie83.484.2tie
- CritPttie1.11.1tie
FactsClaude Sonnet 4.5
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 13.332.919.6+13.3
- AA-Omniscience · Non-hallucinationtie50.950.7tie
Images and chartsQwen3.6 27B
- CharXiv (RQ)Qwen3.6 27B by 11.267.278.4+11.2
- MathVistaQwen3.6 27B by 7.679.887.4+7.6
- MMMU-ProQwen3.6 27B by 5.968.774.6+5.9
- MMMUQwen3.6 27B by 3.379.682.9+3.3
MathQwen3.6 27B
- IMOAnswerBenchQwen3.6 27B by 14.965.980.8+14.9
- FrontierMath Tiers 1-3 (v2)Qwen3.6 27B by 11.223.935.1+11.2
Following instructionsQwen3.6 27B
- IFBenchQwen3.6 27B by 10.357.367.6+10.3
Other results14 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 Feb. 2025Qwen3.6 27B by 26.367.593.8+26.3
- AA-OmniscienceClaude Sonnet 4.5 by 19.9-0.1-20+19.9
- HMMT 2025Qwen3.6 27B by 16.174.690.7+16.1
- τ²-Bench Telecom (AA run)Qwen3.6 27B by 16.178.194.2+16.1
- RealWorldQAQwen3.6 27B by 13.870.384.1+13.8
- CC-OCRQwen3.6 27B by 13.168.181.2+13.1
- Terminal-Bench 2.0Qwen3.6 27B by 9.35059.3+9.3
- HMMT Nov. 2025Qwen3.6 27B by 981.790.7+9
- AA Agentic IndexQwen3.6 27B by 2.617.520.1+2.6
- MMLU-ReduxClaude Sonnet 4.5 by 2.195.693.5+2.1
- Artificial Analysis Coding IndexQwen3.6 27B by 1.652.153.7+1.6
- SimpleVQAClaude Sonnet 4.5 by 1.557.656.1+1.5
- MMLU-ProClaude Sonnet 4.5 by 1.387.586.2+1.3
- AA Intelligencetie20.721.4tie
Questions people ask
Which is better, Claude Sonnet 4.5 or Qwen3.6 27B?
Qwen3.6 27B wins six of the eight areas we test: coding, reasoning, images and charts, math, long documents and following instructions. Claude Sonnet 4.5 wins facts. They are level on agents.
Which is better for coding?
Qwen3.6 27B. It wins 4 of the 7 coding tests both models report; Claude Sonnet 4.5 wins 1, and 2 are ties.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; Qwen3.6 27B costs $0.60 and $3.60. That makes Qwen3.6 27B about 77% cheaper for the same work.
How do you compare the two?
We use the 37 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 14 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.