Gemini 3 Pro vs Qwen3.6 Plus
Wins 3 of 8 areas
Reasoning · Facts · Images and charts
Wins 3 of 8 areas
Coding · Math · Following instructions
The two are evenly matched.Gemini 3 Pro is better at reasoning and images and charts; Qwen3.6 Plus at coding and math.
Scores updated · 43 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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 software15Qwen3.6 Plus5 of 7 tests · 1 tie
- MathCompetition and research-level math02Qwen3.6 Plus2 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked01Qwen3.6 Plus1 of 1 test
- ReasoningHard problems that need careful thinking30Gemini 3 Pro3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20Gemini 3 Pro2 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up21Gemini 3 Pro2 of 3 tests
- AgentsCarrying out multi-step tasks on its own11Even1 each
- Long documentsFinding answers in very long texts11Even1 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 75% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.6 Plus pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+56.9points ahead
- Multi-step tasks using many real software toolsMCP Atlas+20points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+13.3points ahead
Where Gemini 3 Pro pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+29.4points ahead
- Short factual questions, answered correctlySimpleQA Verified+28.8points ahead
- Code for real scientific research problemsSciCode+15.4points 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.
CodingQwen3.6 Plus
- SciCodeGemini 3 Pro by 15.456.140.7+15.4
- SWE-bench ProQwen3.6 Plus by 13.343.356.6+13.3
- SWE-bench MultilingualQwen3.6 Plus by 8.86573.8+8.8
- SWE-bench VerifiedQwen3.6 Plus by 2.676.278.8+2.6
- Terminal-Bench HardQwen3.6 Plus by 2.241.743.9+2.2
- LMArena · WebDevQwen3.6 Plus by 21 rating points14401461+21 rating
- LiveCodeBench v6tie87.487.1tie
AgentsEven
ReasoningGemini 3 Pro
- Humanity's Last ExamGemini 3 Pro by 11.939.727.8+11.9
- CritPtGemini 3 Pro by 6.29.12.9+6.2
- GPQA DiamondGemini 3 Pro by 2.690.888.2+2.6
FactsGemini 3 Pro
- AA-Omniscience · Non-hallucinationQwen3.6 Plus by 56.98.565.4+56.9
- AA-Omniscience · AccuracyGemini 3 Pro by 29.455.826.4+29.4
- SimpleQA VerifiedGemini 3 Pro by 28.872.944.1+28.8
Images and chartsGemini 3 Pro
- Video-MMEGemini 3 Pro by 4.288.484.2+4.2
- MMMU-ProGemini 3 Pro by 2.280.278+2.2
- CharXiv (RQ)tie81.481.5tie
MathQwen3.6 Plus
- AIME 2026Qwen3.6 Plus by 3.691.795.3+3.6
- HMMT Feb. 2026Qwen3.6 Plus by 1.486.487.8+1.4
- IMOAnswerBenchtie83.183.8tie
Long documentsEven
- LongBench v2Gemini 3 Pro by 6.268.262+6.2
- AA-LCRQwen3.6 Plus by 2.37678.3+2.3
Following instructionsQwen3.6 Plus
- IFBenchQwen3.6 Plus by 4.870.475.2+4.8
Other results19 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 Agentic IndexGemini 3 Pro by 235229+23
- AA-OmniscienceGemini 3 Pro by 14.415.30.9+14.4
- τ²-Bench Telecom (AA run)Qwen3.6 Plus by 10.687.197.7+10.6
- frontiermath_tier_4_v1Gemini 3 Pro by 10.518.88.3+10.5
- Artificial Analysis Coding IndexQwen3.6 Plus by 846.554.5+8
- Terminal-Bench 2.0Qwen3.6 Plus by 7.454.261.6+7.4
- MLVUQwen3.6 Plus by 680.786.7+6
- HLE (with tools)Qwen3.6 Plus by 4.845.850.6+4.8
- ScreenSpot-Pro (No tools)Gemini 3 Pro by 4.572.768.2+4.5
- VideoMMMUGemini 3 Pro by 3.687.684+3.6
- ToolathlonQwen3.6 Plus by 3.436.439.8+3.4
- OmniDocBench 1.5Qwen3.6 Plus by 2.788.591.2+2.7
- LiveBenchGemini 3 Pro by 2.573.470.8+2.5
- SimpleVQAGemini 3 Pro by 2.469.767.3+2.4
- MMMLUGemini 3 Pro by 2.391.889.5+2.3
- MATH-VisionQwen3.6 Plus by 1.986.188+1.9
- MMLU-ProGemini 3 Pro by 1.690.188.5+1.6
- HMMT Nov. 2025Qwen3.6 Plus by 1.393.394.6+1.3
- AA IntelligenceGemini 3 Pro by 12827+1
Questions people ask
Which is better, Gemini 3 Pro or Qwen3.6 Plus?
Gemini 3 Pro and Qwen3.6 Plus each win three of the eight areas we test. Gemini 3 Pro wins reasoning, facts and images and charts; Qwen3.6 Plus wins coding, math and following instructions. Qwen3.6 Plus costs 75% less. They are level on agents and long documents.
Which is better for coding?
Qwen3.6 Plus. It wins 5 of the 7 coding tests both models report; Gemini 3 Pro wins 1, and 1 is a tie.
Which is cheaper?
Gemini 3 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Qwen3.6 Plus costs $0.50 and $3.00. That makes Qwen3.6 Plus about 75% 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 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 19 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.