Qwen3.6 Plus vs Qwen3 Max (Reasoning)
Wins 5 of 6 areas
Coding · Reasoning · Math · Long documents · Following instructions
Wins 0 of 6 areas
—
Qwen3.6 Plus is the stronger all-rounder.
Scores updated · 28 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 software40Qwen3.6 Plus4 of 4 tests
- ReasoningHard problems that need careful thinking20Qwen3.6 Plus2 of 3 tests · 1 tie
- Long documentsFinding answers in very long texts20Qwen3.6 Plus2 of 2 tests
- MathCompetition and research-level math10Qwen3.6 Plus1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked10Qwen3.6 Plus1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Following instructions rests on a single test.
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 Plus costs 51% 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 Qwen3.6 Plus pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+60.1points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+19.7points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+7.1points ahead
Where Qwen3 Max (Reasoning) pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+3.4points ahead
Every test, side by side
All 28 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.6 Plus
- Terminal-Bench HardQwen3.6 Plus by 19.743.924.2+19.7
- SWE-bench MultilingualQwen3.6 Plus by 7.173.866.7+7.1
- SWE-bench VerifiedQwen3.6 Plus by 3.578.875.3+3.5
- LiveCodeBench v6Qwen3.6 Plus by 1.287.185.9+1.2
ReasoningQwen3.6 Plus
- GPQA DiamondQwen3.6 Plus by 2.188.286.1+2.1
- CritPtQwen3.6 Plus by 1.22.91.7+1.2
- Humanity's Last Examtie27.828tie
FactsEven
- AA-Omniscience · Non-hallucinationQwen3.6 Plus by 60.165.45.3+60.1
- AA-Omniscience · AccuracyQwen3 Max (Reasoning) by 3.426.429.8+3.4
Long documentsQwen3.6 Plus
- AA-LCRQwen3.6 Plus by 478.374.3+4
- LongBench v2Qwen3.6 Plus by 1.46260.6+1.4
Following instructionsQwen3.6 Plus
- IFBenchQwen3.6 Plus by 4.575.270.7+4.5
Other results14 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.
- Terminal-Bench 2.0Qwen3.6 Plus by 39.161.622.5+39.1
- AA-OmniscienceQwen3.6 Plus by 37.50.9-36.6+37.5
- ToolathlonQwen3.6 Plus by 2139.818.8+21
- WideSearchQwen3.6 Plus by 16.474.357.9+16.4
- MCPMarkQwen3.6 Plus by 14.748.233.5+14.7
- τ²-Bench Telecom (AA run)Qwen3.6 Plus by 14.197.783.6+14.1
- DeepPlanningQwen3.6 Plus by 12.841.528.7+12.8
- AA IntelligenceQwen3.6 Plus by 5.72721.3+5.7
- MMMLUQwen3.6 Plus by 5.189.584.4+5.1
- SuperGPQAQwen3.6 Plus by 4.371.667.3+4.3
- VITA-BenchQwen3.6 Plus by 3.444.340.9+3.4
- MMLU-ProQwen3.6 Plus by 2.888.585.7+2.8
- MMLU-ReduxQwen3.6 Plus by 1.794.592.8+1.7
- C-Evaltie93.393.7tie
Questions people ask
Which is better, Qwen3.6 Plus or Qwen3 Max (Reasoning)?
Qwen3.6 Plus wins five of the six areas where both have results: coding, reasoning, math, long documents and following instructions. Qwen3 Max (Reasoning) wins none. They are level on facts.
Which is better for coding?
Qwen3.6 Plus. It wins 4 of the 4 coding tests both models report; Qwen3 Max (Reasoning) wins none.
Which is cheaper?
Qwen3.6 Plus costs $0.50 per million input tokens and $3.00 per million output tokens; Qwen3 Max (Reasoning) costs $1.20 and $6.00. That makes Qwen3.6 Plus about 51% cheaper for the same work.
How do you compare the two?
We use the 28 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 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.