Claude Opus 4.6 vs Qwen3.6 35B A3B
Wins 5 of 8 areas
Coding · Agents · Reasoning · Math · Long documents
Wins 2 of 8 areas
Images and charts · Following instructions
Claude Opus 4.6 is the stronger all-rounder.Qwen3.6 35B A3B is cheaper and better at images and charts.
Scores updated · 39 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 software60Claude Opus 4.66 of 6 tests
- ReasoningHard problems that need careful thinking30Claude Opus 4.63 of 3 tests
- MathCompetition and research-level math31Claude Opus 4.63 of 4 tests
- AgentsCarrying out multi-step tasks on its own20Claude Opus 4.62 of 3 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude Opus 4.61 of 1 test
- Images and chartsUnderstanding pictures, charts and video01Qwen3.6 35B A3B1 of 3 tests · 2 ties
- Following instructionsDoing exactly what it is asked01Qwen3.6 35B A3B1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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 35B A3B costs 91% 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 Opus 4.6 pulls ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+45.6points ahead
- Real work tasks from 44 professionsGDPVal+36.1points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+35.3points ahead
Where Qwen3.6 35B A3B pulls ahead
- Reads and reasons about text in imagesOCRBenchv2+17.1points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+12.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+11.3points ahead
Every test, side by side
All 39 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.6
- SciCodeClaude Opus 4.6 by 15.351.936.6+15.3
- Terminal-Bench HardClaude Opus 4.6 by 11.446.234.8+11.4
- SWE-bench MultilingualClaude Opus 4.6 by 10.677.867.2+10.6
- LiveCodeBench v6Claude Opus 4.6 by 8.488.880.4+8.4
- SWE-bench VerifiedClaude Opus 4.6 by 7.480.873.4+7.4
- SWE-bench ProClaude Opus 4.6 by 3.953.449.5+3.9
AgentsClaude Opus 4.6
- GDPValClaude Opus 4.6 by 36.155.919.8+36.1
- BrowseCompClaude Opus 4.6 by 35.38448.7+35.3
- MCP Atlastie62.762.8tie
ReasoningClaude Opus 4.6
- Humanity's Last ExamClaude Opus 4.6 by 17.739.922.2+17.7
- CritPtClaude Opus 4.6 by 12.312.60.3+12.3
- GPQA DiamondClaude Opus 4.6 by 5.589.684.1+5.5
FactsEven
- AA-Omniscience · AccuracyClaude Opus 4.6 by 28.24718.8+28.2
- AA-Omniscience · Non-hallucinationQwen3.6 35B A3B by 12.337.249.5+12.3
Images and chartsQwen3.6 35B A3B
- OCRBenchv2Qwen3.6 35B A3B by 17.148.465.5+17.1
- CharXiv (RQ)tie77.478tie
- MMMU-Protie75.475tie
MathClaude Opus 4.6
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.6 by 45.66620.4+45.6
- HMMT Feb. 2026Claude Opus 4.6 by 12.696.283.6+12.6
- AIME 2026Claude Opus 4.6 by 496.792.7+4
- IMOAnswerBenchQwen3.6 35B A3B by 3.675.378.9+3.6
Following instructionsQwen3.6 35B A3B
- IFBenchQwen3.6 35B A3B by 11.353.164.4+11.3
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.
- AA Agentic IndexClaude Opus 4.6 by 52.667.615+52.6
- AA-OmniscienceClaude Opus 4.6 by 35.913.7-22.2+35.9
- ToolathlonClaude Opus 4.6 by 29.956.826.9+29.9
- NL2RepoClaude Opus 4.6 by 20.449.829.4+20.4
- Tool-DecathlonClaude Opus 4.6 by 20.347.226.9+20.3
- MCPMarkClaude Opus 4.6 by 19.756.737+19.7
- Terminal-Bench 2.0Claude Opus 4.6 by 13.965.451.5+13.9
- AA IntelligenceClaude Opus 4.6 by 13.731.918.2+13.7
- RealWorldQAQwen3.6 35B A3B by 11.473.985.3+11.4
- LVBenchQwen3.6 35B A3B by 8.46371.4+8.4
- HMMT Nov. 2025Claude Opus 4.6 by 7.296.389.1+7.2
- Artificial Analysis Coding IndexClaude Opus 4.6 by 6.248.141.9+6.2
- τ³-BenchClaude Opus 4.6 by 5.272.467.2+5.2
- MMLU-ProClaude Opus 4.6 by 3.989.185.2+3.9
- τ²-Bench Telecom (AA run)Qwen3.6 35B A3B by 3.292.195.3+3.2
- OCRBench v2 (Chinese)Qwen3.6 35B A3B by 159.860.8+1
Questions people ask
Which is better, Claude Opus 4.6 or Qwen3.6 35B A3B?
Claude Opus 4.6 wins five of the eight areas we test: coding, agents, reasoning, math and long documents. Qwen3.6 35B A3B wins images and charts and following instructions, and costs 91% less. They are level on facts.
Which is better for coding?
Claude Opus 4.6. It wins 6 of the 6 coding tests both models report; Qwen3.6 35B A3B wins none.
Which is cheaper?
Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; Qwen3.6 35B A3B costs $0.38 and $2.25. That makes Qwen3.6 35B A3B about 91% cheaper for the same work.
How do you compare the two?
We use the 39 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 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.