Claude Opus 4.5 vs Qwen3.6 35B A3B
Wins 4 of 8 areas
Coding · Reasoning · Math · Long documents
Wins 2 of 8 areas
Images and charts · Following instructions
Claude Opus 4.5 wins more areas, narrowly.Qwen3.6 35B A3B is cheaper and better at images and charts.
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 software51Claude Opus 4.55 of 6 tests
- MathCompetition and research-level math40Claude Opus 4.54 of 4 tests
- ReasoningHard problems that need careful thinking30Claude Opus 4.53 of 3 tests
- Long documentsFinding answers in very long texts10Claude Opus 4.51 of 1 test
- Images and chartsUnderstanding pictures, charts and video04Qwen3.6 35B A3B4 of 4 tests
- Following instructionsDoing exactly what it is asked01Qwen3.6 35B A3B1 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 each · 1 tie
- 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 4.5 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+27.8points ahead
- Real work tasks from 44 professionsGDPVal+27.5points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+14points ahead
Where Qwen3.6 35B A3B pulls ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+60.2points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+11.7points ahead
- Reasoning about charts from research papersCharXiv (RQ)+10.8points 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.
CodingClaude Opus 4.5
- SWE-bench MultilingualQwen3.6 35B A3B by 60.2767.2+60.2
- SciCodeClaude Opus 4.5 by 12.949.536.6+12.9
- Terminal-Bench HardClaude Opus 4.5 by 12.24734.8+12.2
- SWE-bench VerifiedClaude Opus 4.5 by 7.580.973.4+7.5
- LiveCodeBench v6Claude Opus 4.5 by 4.484.880.4+4.4
- SWE-bench ProClaude Opus 4.5 by 2.55249.5+2.5
AgentsEven
- GDPValClaude Opus 4.5 by 27.547.319.8+27.5
- BrowseCompQwen3.6 35B A3B by 11.73748.7+11.7
- MCP Atlastie62.362.8tie
ReasoningClaude Opus 4.5
- Humanity's Last ExamClaude Opus 4.5 by 7.930.122.2+7.9
- CritPtClaude Opus 4.5 by 4.34.60.3+4.3
- GPQA DiamondClaude Opus 4.5 by 2.586.684.1+2.5
FactsEven
- AA-Omniscience · AccuracyClaude Opus 4.5 by 27.846.618.8+27.8
- AA-Omniscience · Non-hallucinationQwen3.6 35B A3B by 10.53949.5+10.5
Images and chartsQwen3.6 35B A3B
- CharXiv (RQ)Qwen3.6 35B A3B by 10.867.278+10.8
- MathVistaQwen3.6 35B A3B by 6.280.286.4+6.2
- MMMUQwen3.6 35B A3B by 180.781.7+1
- MMMU-ProQwen3.6 35B A3B by 17475+1
MathClaude Opus 4.5
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.5 by 1434.420.4+14
- IMOAnswerBenchClaude Opus 4.5 by 5.18478.9+5.1
- AIME 2026Claude Opus 4.5 by 2.495.192.7+2.4
- HMMT Feb. 2026Claude Opus 4.5 by 1.785.383.6+1.7
Following instructionsQwen3.6 35B A3B
- IFBenchQwen3.6 35B A3B by 6.45864.4+6.4
Other results21 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 4.5 by 44.659.615+44.6
- AA-OmniscienceClaude Opus 4.5 by 36.214-22.2+36.2
- SkillsBench Avg5Claude Opus 4.5 by 16.645.328.7+16.6
- ToolathlonClaude Opus 4.5 by 16.643.526.9+16.6
- QwenWebBenchClaude Opus 4.5 by 139 rating points15361397+139 rating
- NL2RepoClaude Opus 4.5 by 13.843.229.4+13.8
- AA IntelligenceClaude Opus 4.5 by 10.929.118.2+10.9
- SimpleVQAClaude Opus 4.5 by 10.869.758.9+10.8
- Claw-Eval AvgClaude Opus 4.5 by 7.976.668.7+7.9
- Terminal-Bench 2.0Claude Opus 4.5 by 7.859.351.5+7.8
- Artificial Analysis Coding IndexClaude Opus 4.5 by 5.947.841.9+5.9
- SuperGPQAClaude Opus 4.5 by 5.970.664.7+5.9
- τ²-Bench Telecom (AA run)Qwen3.6 35B A3B by 5.889.595.3+5.8
- MMLU-ProClaude Opus 4.5 by 4.389.585.2+4.3
- HMMT Nov. 2025Claude Opus 4.5 by 4.293.389.1+4.2
- MMLU-ReduxClaude Opus 4.5 by 2.395.693.3+2.3
- C-EvalClaude Opus 4.5 by 2.292.290+2.2
- HMMT Feb. 2025Claude Opus 4.5 by 2.292.990.7+2.2
- OmniDocBench 1.5Qwen3.6 35B A3B by 2.287.789.9+2.2
- VideoMMMUtie84.483.7tie
- QwenClawBenchtie52.352.6tie
Questions people ask
Which is better, Claude Opus 4.5 or Qwen3.6 35B A3B?
Claude Opus 4.5 wins four of the eight areas we test: coding, reasoning, math and long documents. Qwen3.6 35B A3B wins images and charts and following instructions, and costs 91% less. They are level on agents and facts.
Which is better for coding?
Claude Opus 4.5. It wins 5 of the 6 coding tests both models report; Qwen3.6 35B A3B wins 1.
Which is cheaper?
Claude Opus 4.5 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 45 benchmark tests both models have published scores on. The verdict counts the 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 21 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.