Claude Sonnet 4 vs Qwen3.5 27B
Wins 1 of 7 areas
Facts
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Qwen3.5 27B is the stronger all-rounder.Claude Sonnet 4 is better at facts.
Scores updated · 37 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 software04Qwen3.5 27B4 of 6 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own03Qwen3.5 27B3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video03Qwen3.5 27B3 of 3 tests
- ReasoningHard problems that need careful thinking02Qwen3.5 27B2 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked02Qwen3.5 27B2 of 2 tests
- Long documentsFinding answers in very long texts01Qwen3.5 27B1 of 1 test
- FactsGetting facts right instead of making them up30Claude Sonnet 43 of 3 tests
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.
Qwen3.5 27B costs 85% 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 Qwen3.5 27B pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+48.8points ahead
- Recent programming contest problemsLiveCodeBench v6+32.2points ahead
- Real work tasks from 44 professionsGDPVal+23.3points ahead
Where Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+52.4points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+2points 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.
CodingQwen3.5 27B
- LiveCodeBench v6Qwen3.5 27B by 32.248.580.7+32.2
- SWE-bench MultilingualQwen3.5 27B by 12.456.969.3+12.4
- SWE-bench ProQwen3.5 27B by 8.542.751.2+8.5
- Terminal-Bench HardQwen3.5 27B by 1.531.132.6+1.5
- SciCodetie4039.5tie
- SWE-bench Verifiedtie72.772.4tie
AgentsQwen3.5 27B
- BrowseCompQwen3.5 27B by 48.812.261+48.8
- GDPValQwen3.5 27B by 23.39.733+23.3
- OSWorld-VerifiedQwen3.5 27B by 1442.256.2+14
ReasoningQwen3.5 27B
- Humanity's Last ExamQwen3.5 27B by 13.210.723.9+13.2
- GPQA DiamondQwen3.5 27B by 8.177.785.8+8.1
- CritPttie0.30.9tie
FactsClaude Sonnet 4
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 52.470.918.5+52.4
- AA-Omniscience · AccuracyClaude Sonnet 4 by 222.720.7+2
- Vectara HHEM hallucination ratelower is betterClaude Sonnet 4 by 1.810.312.1+1.8
Images and chartsQwen3.5 27B
- MMMU-ProQwen3.5 27B by 13.261.875+13.2
- MMMUQwen3.5 27B by 7.974.482.3+7.9
- LMArena · VisionQwen3.5 27B by 49 rating points11911240+49 rating
Following instructionsQwen3.5 27B
- IFBenchQwen3.5 27B by 20.954.775.6+20.9
- Multi-ChallengeQwen3.5 27B by 3.757.160.8+3.7
Other results16 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 2025Qwen3.5 27B by 73.915.989.8+73.9
- AA-OmniscienceClaude Sonnet 4 by 44.20.2-44+44.2
- AA Agentic IndexQwen3.5 27B by 3717.654.6+37
- BrowseComp-ZHQwen3.5 27B by 3329.162.1+33
- τ²-Bench Telecom (AA run)Qwen3.5 27B by 29.364.693.9+29.3
- OJBenchQwen3.5 27B by 24.815.340.1+24.8
- SuperGPQAQwen3.5 27B by 9.955.765.6+9.9
- IFEvalQwen3.5 27B by 7.487.695+7.4
- vectara_avg_summary_lengthClaude Sonnet 4 by 51.4 rating points145.894.4+51.4 rating
- AA IntelligenceQwen3.5 27B by 418.922.9+4
- Artificial Analysis Coding IndexClaude Sonnet 4 by 2.737.634.9+2.7
- MMLU-ProQwen3.5 27B by 2.483.786.1+2.4
- vectara_factual_consistencyClaude Sonnet 4 by 1.889.787.9+1.8
- vectara_answer_rateQwen3.5 27B by 1.298.699.8+1.2
- MMMLUtie86.585.9tie
- MMLU-Reduxtie93.693.2tie
Questions people ask
Which is better, Claude Sonnet 4 or Qwen3.5 27B?
Qwen3.5 27B wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. Claude Sonnet 4 wins facts.
Which is better for coding?
Qwen3.5 27B. It wins 4 of the 6 coding tests both models report; Claude Sonnet 4 wins none, and 2 are ties.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; Qwen3.5 27B costs $0.30 and $2.40. That makes Qwen3.5 27B about 85% 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 21 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.