Qwen3.5 27B 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 27B is cheaper.
Scores updated · 40 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 software07Qwen3.7 Max7 of 7 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
- AgentsCarrying out multi-step tasks on its own12Qwen3.7 Max2 of 3 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 27B costs 73% 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+55.9points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+18.2points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+16.6points ahead
Where Qwen3.5 27B pulls ahead
- Real work tasks from 44 professionsGDPVal+1.4points ahead
Every test, side by side
All 40 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.7 Max
- Terminal-Bench HardQwen3.7 Max by 18.232.650.8+18.2
- LMArena · WebDevQwen3.7 Max by 158 rating points13571515+158 rating
- LiveCodeBench v6Qwen3.7 Max by 10.980.791.6+10.9
- SciCodeQwen3.7 Max by 1039.549.5+10
- SWE-bench ProQwen3.7 Max by 9.451.260.6+9.4
- SWE-bench MultilingualQwen3.7 Max by 969.378.3+9
- SWE-bench VerifiedQwen3.7 Max by 872.480.4+8
AgentsQwen3.7 Max
- MCP AtlasQwen3.7 Max by 868.476.4+8
- AA IT-Bench SREQwen3.7 Max by 735.542.5+7
- GDPValQwen3.5 27B by 1.43331.6+1.4
ReasoningQwen3.7 Max
- Humanity's Last ExamQwen3.7 Max by 16.623.940.5+16.6
- CritPtQwen3.7 Max by 12.50.913.4+12.5
- GPQA DiamondQwen3.7 Max by 6.585.892.3+6.5
FactsQwen3.7 Max
- AA-Omniscience · Non-hallucinationQwen3.7 Max by 55.918.574.4+55.9
- AA-Omniscience · AccuracyQwen3.7 Max by 10.420.731.1+10.4
MathQwen3.7 Max
- HMMT Feb. 2026Qwen3.7 Max by 1681.197.1+16
- IMOAnswerBenchQwen3.7 Max by 10.179.990+10.1
- AIME 2026Qwen3.7 Max by 5.391.797+5.3
Following instructionsQwen3.7 Max
- IFBenchQwen3.7 Max by 4.975.680.5+4.9
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 57.5-4413.5+57.5
- Artificial Analysis Coding IndexQwen3.7 Max by 31.134.966+31.1
- AA Agentic IndexQwen3.5 27B by 30.754.623.9+30.7
- Terminal-Bench 2.0Qwen3.7 Max by 28.141.669.7+28.1
- MCPMarkQwen3.7 Max by 24.536.360.8+24.5
- NL2RepoQwen3.7 Max by 19.927.347.2+19.9
- Claw Eval (pass@3)Qwen3.7 Max by 1946.265.2+19
- WideSearchQwen3.7 Max by 14.161.175.2+14.1
- SuperGPQAQwen3.7 Max by 865.673.6+8
- AA IntelligenceQwen3.7 Max by 6.622.929.5+6.6
- BFCLv4Qwen3.7 Max by 6.568.575+6.5
- VITA-BenchQwen3.7 Max by 641.947.9+6
- HMMT Nov. 2025Qwen3.7 Max by 5.289.895+5.2
- MMLU-ProXQwen3.7 Max by 4.882.287+4.8
- IncludeQwen3.7 Max by 4.681.686.2+4.6
- MMMLUQwen3.7 Max by 4.485.990.3+4.4
- MMLU-ProQwen3.7 Max by 3.586.189.6+3.5
- MMLU-ReduxQwen3.7 Max by 1.893.295+1.8
- τ²-Bench Telecom (AA run)tie93.994.7tie
- IFEvaltie9594.3tie
Questions people ask
Which is better, Qwen3.5 27B 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 27B wins none, but costs 73% less.
Which is better for coding?
Qwen3.7 Max. It wins 7 of the 7 coding tests both models report; Qwen3.5 27B wins none.
Which is cheaper?
Qwen3.5 27B costs $0.30 per million input tokens and $2.40 per million output tokens; Qwen3.7 Max costs $2.50 and $7.50. That makes Qwen3.5 27B about 73% cheaper for the same work.
How do you compare the two?
We use the 40 benchmark tests both models have published scores on. The verdict counts the 20 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.