Qwen3.5 35B A3B vs Qwen3.7 Max
Wins 0 of 7 areas
—
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Math · Long documents · Following instructions
Qwen3.7 Max is the stronger all-rounder.Qwen3.5 35B A3B is cheaper.
Scores updated · 42 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 software08Qwen3.7 Max8 of 8 tests
- AgentsCarrying out multi-step tasks on its own04Qwen3.7 Max4 of 4 tests
- ReasoningHard problems that need careful thinking03Qwen3.7 Max3 of 3 tests
- MathCompetition and research-level math03Qwen3.7 Max3 of 3 tests
- FactsGetting facts right instead of making them up02Qwen3.7 Max2 of 2 tests
- Long documentsFinding answers in very long texts01Qwen3.7 Max1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.7 Max1 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 78% 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 Qwen3.7 Max pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+59.8points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+33.7points ahead
- Real work tasks from 44 professionsGDPVal+26points ahead
Where Qwen3.5 35B A3B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 42 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.7 Max
- Terminal-Bench 2.1Qwen3.7 Max by 33.740.874.5+33.7
- LMArena · WebDevQwen3.7 Max by 265 rating points12501515+265 rating
- Terminal-Bench HardQwen3.7 Max by 24.326.550.8+24.3
- SWE-bench MultilingualQwen3.7 Max by 1860.378.3+18
- LiveCodeBench v6Qwen3.7 Max by 1774.691.6+17
- SWE-bench ProQwen3.7 Max by 1644.660.6+16
- SciCodeQwen3.7 Max by 11.837.749.5+11.8
- SWE-bench VerifiedQwen3.7 Max by 11.269.280.4+11.2
AgentsQwen3.7 Max
- GDPValQwen3.7 Max by 265.631.6+26
- AA IT-Bench SREQwen3.7 Max by 2121.542.5+21
- MCP AtlasQwen3.7 Max by 1462.476.4+14
- τ-Bench V3 · BankingQwen3.7 Max by 6.94.911.8+6.9
ReasoningQwen3.7 Max
- Humanity's Last ExamQwen3.7 Max by 19.52140.5+19.5
- CritPtQwen3.7 Max by 12.50.913.4+12.5
- GPQA DiamondQwen3.7 Max by 7.884.592.3+7.8
FactsQwen3.7 Max
- AA-Omniscience · Non-hallucinationQwen3.7 Max by 59.814.674.4+59.8
- AA-Omniscience · AccuracyQwen3.7 Max by 1120.131.1+11
MathQwen3.7 Max
- HMMT Feb. 2026Qwen3.7 Max by 15.381.897.1+15.3
- IMOAnswerBenchQwen3.7 Max by 13.276.890+13.2
- AIME 2026Qwen3.7 Max by 3.793.397+3.7
Following instructionsQwen3.7 Max
- IFBenchQwen3.7 Max by 872.580.5+8
Other results20 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-OmniscienceQwen3.7 Max by 61.6-48.113.5+61.6
- MCPMarkQwen3.7 Max by 33.82760.8+33.8
- Terminal-Bench 2.0Qwen3.7 Max by 29.240.569.7+29.2
- Artificial Analysis Coding IndexQwen3.7 Max by 293766+29
- NL2RepoQwen3.7 Max by 26.720.547.2+26.7
- WideSearchQwen3.7 Max by 18.157.175.2+18.1
- VITA-BenchQwen3.7 Max by 1631.947.9+16
- Claw Eval (pass@3)Qwen3.7 Max by 14.25165.2+14.2
- AA Agentic IndexQwen3.7 Max by 12.111.823.9+12.1
- AA IntelligenceQwen3.7 Max by 10.219.329.5+10.2
- SuperGPQAQwen3.7 Max by 10.263.473.6+10.2
- BFCLv4Qwen3.7 Max by 7.767.375+7.7
- IncludeQwen3.7 Max by 6.579.786.2+6.5
- MMLU-ProXQwen3.7 Max by 68187+6
- HMMT Nov. 2025Qwen3.7 Max by 5.889.295+5.8
- τ²-Bench Telecom (AA run)Qwen3.7 Max by 5.589.294.7+5.5
- MMMLUQwen3.7 Max by 5.185.290.3+5.1
- MMLU-ProQwen3.7 Max by 4.385.389.6+4.3
- IFEvalQwen3.7 Max by 2.491.994.3+2.4
- MMLU-ReduxQwen3.7 Max by 1.793.395+1.7
Questions people ask
Which is better, Qwen3.5 35B A3B or Qwen3.7 Max?
Qwen3.7 Max wins all seven areas where both have results: coding, agents, reasoning, facts, math, long documents and following instructions. Qwen3.5 35B A3B wins none, but costs 78% less.
Which is better for coding?
Qwen3.7 Max. It wins 8 of the 8 coding tests both models report; Qwen3.5 35B A3B wins none.
Which is cheaper?
Qwen3.5 35B A3B costs $0.25 per million input tokens and $2.00 per million output tokens; Qwen3.7 Max costs $2.50 and $7.50. That makes Qwen3.5 35B A3B about 78% cheaper for the same work.
How do you compare the two?
We use the 42 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 20 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.