Qwen3.6 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.Qwen3.6 35B A3B is cheaper.
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 software07Qwen3.7 Max7 of 7 tests
- AgentsCarrying out multi-step tasks on its own04Qwen3.7 Max4 of 4 tests
- MathCompetition and research-level math04Qwen3.7 Max4 of 4 tests
- ReasoningHard problems that need careful thinking03Qwen3.7 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.
Qwen3.6 35B A3B costs 74% 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- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+44.2points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+29.6points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+24.9points ahead
Where Qwen3.6 35B A3B pulls ahead
No clear win on a test scored out of 100.
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.
CodingQwen3.7 Max
- Terminal-Bench 2.1Qwen3.7 Max by 29.644.974.5+29.6
- Terminal-Bench HardQwen3.7 Max by 1634.850.8+16
- SciCodeQwen3.7 Max by 12.936.649.5+12.9
- LiveCodeBench v6Qwen3.7 Max by 11.280.491.6+11.2
- SWE-bench MultilingualQwen3.7 Max by 11.167.278.3+11.1
- SWE-bench ProQwen3.7 Max by 11.149.560.6+11.1
- SWE-bench VerifiedQwen3.7 Max by 773.480.4+7
AgentsQwen3.7 Max
- MCP AtlasQwen3.7 Max by 13.662.876.4+13.6
- GDPValQwen3.7 Max by 11.819.831.6+11.8
- τ-Bench V3 · BankingQwen3.7 Max by 2.59.311.8+2.5
- Terminal-Bench 4.0Qwen3.7 Max by 1.501.5+1.5
ReasoningQwen3.7 Max
- Humanity's Last ExamQwen3.7 Max by 18.322.240.5+18.3
- CritPtQwen3.7 Max by 13.10.313.4+13.1
- GPQA DiamondQwen3.7 Max by 8.284.192.3+8.2
FactsQwen3.7 Max
- AA-Omniscience · Non-hallucinationQwen3.7 Max by 24.949.574.4+24.9
- AA-Omniscience · AccuracyQwen3.7 Max by 12.318.831.1+12.3
MathQwen3.7 Max
- FrontierMath Tiers 1-3 (v2)Qwen3.7 Max by 44.220.464.6+44.2
- HMMT Feb. 2026Qwen3.7 Max by 13.583.697.1+13.5
- IMOAnswerBenchQwen3.7 Max by 11.178.990+11.1
- AIME 2026Qwen3.7 Max by 4.392.797+4.3
Following instructionsQwen3.7 Max
- IFBenchQwen3.7 Max by 16.164.480.5+16.1
Other results15 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 35.7-22.213.5+35.7
- Artificial Analysis Coding IndexQwen3.7 Max by 24.141.966+24.1
- MCPMarkQwen3.7 Max by 23.83760.8+23.8
- Terminal-Bench 2.0Qwen3.7 Max by 18.251.569.7+18.2
- NL2RepoQwen3.7 Max by 17.829.447.2+17.8
- Claw Eval (pass@3)Qwen3.7 Max by 15.25065.2+15.2
- WideSearchQwen3.7 Max by 15.160.175.2+15.1
- VITA-BenchQwen3.7 Max by 12.335.647.9+12.3
- AA IntelligenceQwen3.7 Max by 11.318.229.5+11.3
- AA Agentic IndexQwen3.7 Max by 8.91523.9+8.9
- SuperGPQAQwen3.7 Max by 8.964.773.6+8.9
- HMMT Nov. 2025Qwen3.7 Max by 5.989.195+5.9
- MMLU-ProQwen3.7 Max by 4.485.289.6+4.4
- MMLU-ReduxQwen3.7 Max by 1.793.395+1.7
- τ²-Bench Telecom (AA run)tie95.394.7tie
Questions people ask
Which is better, Qwen3.6 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. Qwen3.6 35B A3B wins none, but costs 74% less.
Which is better for coding?
Qwen3.7 Max. It wins 7 of the 7 coding tests both models report; Qwen3.6 35B A3B wins none.
Which is cheaper?
Qwen3.6 35B A3B costs $0.38 per million input tokens and $2.25 per million output tokens; Qwen3.7 Max costs $2.50 and $7.50. That makes Qwen3.6 35B A3B about 74% 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 22 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.