DeepSeek-V3.2 vs Qwen3.6 35B A3B
Wins 5 of 7 areas
Coding · Agents · Reasoning · Math · Long documents
Wins 1 of 7 areas
Following instructions
DeepSeek-V3.2 is the stronger all-rounder.Qwen3.6 35B A3B is better at following instructions.
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 software41DeepSeek-V3.24 of 7 tests · 2 ties
- ReasoningHard problems that need careful thinking20DeepSeek-V3.22 of 3 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own21DeepSeek-V3.22 of 4 tests · 1 tie
- MathCompetition and research-level math10DeepSeek-V3.21 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts10DeepSeek-V3.21 of 1 test
- 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.
DeepSeek-V3.2 costs 73% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where DeepSeek-V3.2 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+14.2points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+9.5points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+3points ahead
Where Qwen3.6 35B A3B pulls ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+33.9points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+32.2points ahead
- Real work tasks from 44 professionsGDPVal+10points 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.
CodingDeepSeek-V3.2
- SWE-bench ProQwen3.6 35B A3B by 33.915.649.5+33.9
- SWE-bench MultilingualDeepSeek-V3.2 by 370.267.2+3
- LiveCodeBench v6DeepSeek-V3.2 by 2.983.380.4+2.9
- SciCodeDeepSeek-V3.2 by 2.338.936.6+2.3
- Terminal-Bench 2.1DeepSeek-V3.2 by 1.946.844.9+1.9
- Terminal-Bench Hardtie35.634.8tie
- SWE-bench Verifiedtie73.173.4tie
AgentsDeepSeek-V3.2
- GDPValQwen3.6 35B A3B by 109.819.8+10
- τ-Bench V3 · BankingDeepSeek-V3.2 by 9.518.89.3+9.5
- BrowseCompDeepSeek-V3.2 by 2.751.448.7+2.7
- MCP Atlastie62.262.8tie
ReasoningDeepSeek-V3.2
- CritPtDeepSeek-V3.2 by 2.62.90.3+2.6
- Humanity's Last ExamDeepSeek-V3.2 by 2.424.622.2+2.4
- GPQA Diamondtie8484.1tie
FactsEven
- AA-Omniscience · Non-hallucinationQwen3.6 35B A3B by 32.217.349.5+32.2
- AA-Omniscience · AccuracyDeepSeek-V3.2 by 14.23318.8+14.2
MathDeepSeek-V3.2
- AIME 2026DeepSeek-V3.2 by 1.594.292.7+1.5
- IMOAnswerBenchtie78.378.9tie
- HMMT Feb. 2026tie84.183.6tie
Following instructionsQwen3.6 35B A3B
- IFBenchQwen3.6 35B A3B by 3.760.764.4+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.
- Tool-DecathlonDeepSeek-V3.2 by 8.335.226.9+8.3
- ToolathlonDeepSeek-V3.2 by 8.335.226.9+8.3
- GPQA (unspecified)Qwen3.6 35B A3B by 6.179.986+6.1
- Terminal-Bench 2.0Qwen3.6 35B A3B by 5.146.451.5+5.1
- τ²-Bench Telecom (AA run)Qwen3.6 35B A3B by 4.790.695.3+4.7
- AA Agentic IndexDeepSeek-V3.2 by 3.318.315+3.3
- AA IntelligenceDeepSeek-V3.2 by 3.321.518.2+3.3
- Artificial Analysis Coding IndexDeepSeek-V3.2 by 2.344.241.9+2.3
- τ³-BenchDeepSeek-V3.2 by 269.267.2+2
- HMMT Feb. 2025DeepSeek-V3.2 by 1.892.590.7+1.8
- HMMT 2025DeepSeek-V3.2 by 1.190.289.1+1.1
- MCPMarkDeepSeek-V3.2 by 13837+1
- HMMT Nov. 2025tie9089.1tie
- MMLU-Reduxtie93.793.3tie
- AA-Omnisciencetie-22.5-22.2tie
- MMLU-Protie8585.2tie
Questions people ask
Which is better, DeepSeek-V3.2 or Qwen3.6 35B A3B?
DeepSeek-V3.2 wins five of the seven areas where both have results: coding, agents, reasoning, math and long documents. Qwen3.6 35B A3B wins following instructions. They are level on facts.
Which is better for coding?
DeepSeek-V3.2. It wins 4 of the 7 coding tests both models report; Qwen3.6 35B A3B wins 1, and 2 are ties.
Which is cheaper?
DeepSeek-V3.2 costs $0.28 per million input tokens and $0.42 per million output tokens; Qwen3.6 35B A3B costs $0.38 and $2.25. That makes DeepSeek-V3.2 about 73% 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.