Qwen3.7 Max vs Qwen3.7 Plus Preview
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Math · Long documents · Following instructions
Wins 0 of 7 areas
—
Qwen3.7 Max is the stronger all-rounder.Qwen3.7 Plus Preview is cheaper.
Scores updated · 43 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 software70Qwen3.7 Max7 of 7 tests
- ReasoningHard problems that need careful thinking30Qwen3.7 Max3 of 3 tests
- MathCompetition and research-level math30Qwen3.7 Max3 of 3 tests
- FactsGetting facts right instead of making them up20Qwen3.7 Max2 of 2 tests
- AgentsCarrying out multi-step tasks on its own21Qwen3.7 Max2 of 4 tests · 1 tie
- Long documentsFinding answers in very long texts10Qwen3.7 Max1 of 1 test
- Following instructionsDoing exactly what it is asked10Qwen3.7 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.
Qwen3.7 Plus Preview costs 80% 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
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+30.2points ahead
- Real work tasks from 44 professionsGDPVal+18.1points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+13.5points ahead
Where Qwen3.7 Plus Preview pulls ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+5.7points ahead
Every test, side by side
All 43 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 13.574.561+13.5
- Terminal-Bench HardQwen3.7 Max by 3.850.847+3.8
- SciCodeQwen3.7 Max by 3.449.546.1+3.4
- SWE-bench ProQwen3.7 Max by 360.657.6+3
- SWE-bench VerifiedQwen3.7 Max by 2.780.477.7+2.7
- SWE-bench MultilingualQwen3.7 Max by 2.578.375.8+2.5
- LiveCodeBench v6Qwen3.7 Max by 291.689.6+2
AgentsQwen3.7 Max
- GDPValQwen3.7 Max by 18.131.613.5+18.1
- τ-Bench V3 · BankingQwen3.7 Plus Preview by 5.711.817.5+5.7
- MCP AtlasQwen3.7 Max by 3.276.473.2+3.2
- Terminal-Bench 4.0tie1.51tie
ReasoningQwen3.7 Max
- Humanity's Last ExamQwen3.7 Max by 4.940.535.6+4.9
- CritPtQwen3.7 Max by 4.313.49.1+4.3
- GPQA DiamondQwen3.7 Max by 2.392.390+2.3
FactsQwen3.7 Max
- AA-Omniscience · AccuracyQwen3.7 Max by 8.631.122.5+8.6
- AA-Omniscience · Non-hallucinationQwen3.7 Max by 2.174.472.3+2.1
MathQwen3.7 Max
- FrontierMath Tiers 1-3 (v2)Qwen3.7 Max by 30.264.634.4+30.2
- HMMT Feb. 2026Qwen3.7 Max by 4.297.192.9+4.2
- IMOAnswerBenchQwen3.7 Max by 49086+4
Following instructionsQwen3.7 Max
- IFBenchQwen3.7 Max by 2.580.578+2.5
Other results22 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 12.413.51.1+12.4
- Finance Agent v2Qwen3.7 Max by 10.248.438.2+10.2
- Artificial Analysis Coding IndexQwen3.7 Max by 10.16655.9+10.1
- NL2RepoQwen3.7 Max by 6.147.241.1+6.1
- DeepSWE 1.1Qwen3.7 Max by 5.121.616.5+5.1
- AA IntelligenceQwen3.7 Max by 4.329.525.2+4.3
- AA Agentic IndexQwen3.7 Max by 4.223.919.7+4.2
- JobBenchQwen3.7 Max by 3.731.327.6+3.7
- IncludeQwen3.7 Max by 3.286.283+3.2
- Claw Eval (pass@3)Qwen3.7 Max by 2.565.262.7+2.5
- VITA-BenchQwen3.7 Max by 2.347.945.6+2.3
- SuperGPQAQwen3.7 Max by 2.273.671.4+2.2
- BFCLv4Qwen3.7 Max by 2.17572.9+2.1
- MCPMarkQwen3.7 Max by 2.160.858.7+2.1
- τ²-Bench Telecom (AA run)Qwen3.7 Max by 1.794.793+1.7
- MMLU-ProXQwen3.7 Max by 1.68785.4+1.6
- MMMLUQwen3.7 Max by 1.390.389+1.3
- MMLU-ProQwen3.7 Max by 1.189.688.5+1.1
- Toolathlon Verifiedtie49.750.6tie
- Terminal-Bench 2.0tie69.770.3tie
- MMLU-Reduxtie9594.5tie
- IFEvaltie94.394.6tie
Questions people ask
Which is better, Qwen3.7 Max or Qwen3.7 Plus Preview?
Qwen3.7 Max wins all seven areas where both have results: coding, agents, reasoning, facts, math, long documents and following instructions. Qwen3.7 Plus Preview wins none, but costs 80% less.
Which is better for coding?
Qwen3.7 Max. It wins 7 of the 7 coding tests both models report; Qwen3.7 Plus Preview wins none.
Which is cheaper?
Qwen3.7 Max costs $2.50 per million input tokens and $7.50 per million output tokens; Qwen3.7 Plus Preview costs $0.40 and $1.60. That makes Qwen3.7 Plus Preview about 80% cheaper for the same work.
How do you compare the two?
We use the 43 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 22 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.