Claude Sonnet 4.6 vs Qwen3.5 35B A3B
Wins 5 of 7 areas
Coding · Agents · Reasoning · Facts · Long documents
Wins 2 of 7 areas
Images and charts · Following instructions
Claude Sonnet 4.6 is the stronger all-rounder.Qwen3.5 35B A3B is cheaper and better at images and charts.
Scores updated · 41 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 software60Claude Sonnet 4.66 of 6 tests
- AgentsCarrying out multi-step tasks on its own51Claude Sonnet 4.65 of 6 tests
- ReasoningHard problems that need careful thinking30Claude Sonnet 4.63 of 3 tests
- FactsGetting facts right instead of making them up20Claude Sonnet 4.62 of 3 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude Sonnet 4.61 of 1 test
- Images and chartsUnderstanding pictures, charts and video01Qwen3.5 35B A3B1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked01Qwen3.5 35B A3B1 of 1 test
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.
Qwen3.5 35B A3B costs 88% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Sonnet 4.6 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+37points ahead
- Real work tasks from 44 professionsGDPVal+31.1points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+30.4points ahead
Where Qwen3.5 35B A3B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+15.9points ahead
- Reasoning about charts from research papersCharXiv (RQ)+5.9points ahead
- Multi-step tasks using many real software toolsMCP Atlas+1.1points ahead
Every test, side by side
All 41 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.6
- Terminal-Bench 2.1Claude Sonnet 4.6 by 30.471.240.8+30.4
- LMArena · WebDevClaude Sonnet 4.6 by 272 rating points15221250+272 rating
- Terminal-Bench HardClaude Sonnet 4.6 by 26.55326.5+26.5
- SWE-bench ProClaude Sonnet 4.6 by 13.558.144.6+13.5
- SciCodeClaude Sonnet 4.6 by 12.450.137.7+12.4
- SWE-bench VerifiedClaude Sonnet 4.6 by 10.479.669.2+10.4
AgentsClaude Sonnet 4.6
- GDPValClaude Sonnet 4.6 by 31.136.75.6+31.1
- τ-Bench V3 · BankingClaude Sonnet 4.6 by 29.534.44.9+29.5
- AA IT-Bench SREClaude Sonnet 4.6 by 18.339.821.5+18.3
- OSWorld-VerifiedClaude Sonnet 4.6 by 1872.554.5+18
- BrowseCompClaude Sonnet 4.6 by 13.774.761+13.7
- MCP AtlasQwen3.5 35B A3B by 1.161.362.4+1.1
ReasoningClaude Sonnet 4.6
- Humanity's Last ExamClaude Sonnet 4.6 by 12.633.621+12.6
- GPQA DiamondClaude Sonnet 4.6 by 387.584.5+3
- CritPtClaude Sonnet 4.6 by 2.23.10.9+2.2
FactsClaude Sonnet 4.6
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.6 by 3751.614.6+37
- AA-Omniscience · AccuracyClaude Sonnet 4.6 by 20.840.920.1+20.8
- Vectara HHEM hallucination ratelower is bettertie10.610.5tie
Images and chartsQwen3.5 35B A3B
- CharXiv (RQ)Qwen3.5 35B A3B by 5.971.677.5+5.9
- MMMU-Protie73.372.7tie
Following instructionsQwen3.5 35B A3B
- IFBenchQwen3.5 35B A3B by 15.956.672.5+15.9
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.
- AA-OmniscienceClaude Sonnet 4.6 by 60.312.2-48.1+60.3
- Artificial Analysis Coding IndexClaude Sonnet 4.6 by 266337+26
- AA Agentic IndexClaude Sonnet 4.6 by 21.333.111.8+21.3
- Terminal-Bench 2.0Claude Sonnet 4.6 by 18.659.140.5+18.6
- AgentWorldBench - SWEClaude Sonnet 4.6 by 16.964.547.6+16.9
- τ²-Bench Telecom (AA run)Qwen3.5 35B A3B by 13.575.789.2+13.5
- AgentWorldBench - MCPClaude Sonnet 4.6 by 12.17057.9+12.1
- AgentWorldBench - TerminalClaude Sonnet 4.6 by 10.95746.1+10.9
- AA IntelligenceClaude Sonnet 4.6 by 10.830.119.3+10.8
- AgentWorldBench - OverallClaude Sonnet 4.6 by 8.35647.7+8.3
- AgentWorldBench - OSClaude Sonnet 4.6 by 6.963.256.3+6.9
- GPQA (unspecified)Claude Sonnet 4.6 by 5.789.984.2+5.7
- AgentWorldBench - AndroidClaude Sonnet 4.6 by 4.85853.2+4.8
- MMMLUClaude Sonnet 4.6 by 4.189.385.2+4.1
- AgentWorldBench - WebClaude Sonnet 4.6 by 3.750.847.1+3.7
- AgentWorldBench - SearchClaude Sonnet 4.6 by 2.828.826+2.8
- vectara_avg_summary_lengthClaude Sonnet 4.6 by 19.8 rating points114.794.9+19.8 rating
- vectara_answer_ratetie99.999.8tie
- vectara_factual_consistencytie89.489.5tie
Questions people ask
Which is better, Claude Sonnet 4.6 or Qwen3.5 35B A3B?
Claude Sonnet 4.6 wins five of the seven areas where both have results: coding, agents, reasoning, facts and long documents. Qwen3.5 35B A3B wins images and charts and following instructions, and costs 88% less.
Which is better for coding?
Claude Sonnet 4.6. It wins 6 of the 6 coding tests both models report; Qwen3.5 35B A3B wins none.
Which is cheaper?
Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; Qwen3.5 35B A3B costs $0.25 and $2.00. That makes Qwen3.5 35B A3B about 88% cheaper for the same work.
How do you compare the two?
We use the 41 benchmark tests both models have published scores on. The verdict counts the 22 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.