Gemini 3 Pro vs Qwen3.5 35B A3B
Wins 5 of 8 areas
Coding · Reasoning · Images and charts · Math · Long documents
Wins 2 of 8 areas
Agents · Facts
Gemini 3 Pro is the stronger all-rounder.Qwen3.5 35B A3B is cheaper and better at agents.
Both rank among the ten best models we track in images and charts.
Scores updated · 53 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 software61Gemini 3 Pro6 of 7 tests
- ReasoningHard problems that need careful thinking30Gemini 3 Pro3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video31Gemini 3 Pro3 of 5 tests · 1 tie
- Long documentsFinding answers in very long texts20Gemini 3 Pro2 of 2 tests
- MathCompetition and research-level math21Gemini 3 Pro2 of 3 tests
- AgentsCarrying out multi-step tasks on its own12Qwen3.5 35B A3B2 of 3 tests
- FactsGetting facts right instead of making them up12Qwen3.5 35B A3B2 of 3 tests
- Following instructionsDoing exactly what it is asked11Even1 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 35B A3B costs 84% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Gemini 3 Pro pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+35.7points ahead
- Real work tasks from 44 professionsGDPVal+28.6points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+18.7points ahead
Where Qwen3.5 35B A3B pulls ahead
- Multi-step tasks using many real software toolsMCP Atlas+8.3points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+6.1points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+2.1points ahead
Every test, side by side
All 53 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3 Pro
- LMArena · WebDevGemini 3 Pro by 190 rating points14401250+190 rating
- SciCodeGemini 3 Pro by 18.456.137.7+18.4
- Terminal-Bench HardGemini 3 Pro by 15.241.726.5+15.2
- LiveCodeBench v6Gemini 3 Pro by 12.887.474.6+12.8
- SWE-bench VerifiedGemini 3 Pro by 776.269.2+7
- SWE-bench MultilingualGemini 3 Pro by 4.76560.3+4.7
- SWE-bench ProQwen3.5 35B A3B by 1.343.344.6+1.3
AgentsQwen3.5 35B A3B
- GDPValGemini 3 Pro by 28.634.25.6+28.6
- MCP AtlasQwen3.5 35B A3B by 8.354.162.4+8.3
- BrowseCompQwen3.5 35B A3B by 1.859.261+1.8
ReasoningGemini 3 Pro
- Humanity's Last ExamGemini 3 Pro by 18.739.721+18.7
- CritPtGemini 3 Pro by 8.29.10.9+8.2
- GPQA DiamondGemini 3 Pro by 6.390.884.5+6.3
FactsQwen3.5 35B A3B
- AA-Omniscience · AccuracyGemini 3 Pro by 35.755.820.1+35.7
- AA-Omniscience · Non-hallucinationQwen3.5 35B A3B by 6.18.514.6+6.1
- Vectara HHEM hallucination ratelower is betterQwen3.5 35B A3B by 3.113.610.5+3.1
Images and chartsGemini 3 Pro
- MMMU-ProGemini 3 Pro by 7.580.272.7+7.5
- CharXiv (RQ)Gemini 3 Pro by 3.981.477.5+3.9
- MathVistaGemini 3 Pro by 3.689.886.2+3.6
- OCRBenchv2Qwen3.5 35B A3B by 1.963.465.3+1.9
- OCRBenchtie90.391tie
MathGemini 3 Pro
- IMOAnswerBenchGemini 3 Pro by 6.383.176.8+6.3
- HMMT Feb. 2026Gemini 3 Pro by 4.686.481.8+4.6
- AIME 2026Qwen3.5 35B A3B by 1.691.793.3+1.6
Long documentsGemini 3 Pro
- LongBench v2Gemini 3 Pro by 9.268.259+9.2
- AA-LCRGemini 3 Pro by 47672+4
Following instructionsEven
- Multi-ChallengeGemini 3 Pro by 5.765.760+5.7
- IFBenchQwen3.5 35B A3B by 2.170.472.5+2.1
Other results25 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-OmniscienceGemini 3 Pro by 63.415.3-48.1+63.4
- AA Agentic IndexGemini 3 Pro by 40.25211.8+40.2
- Terminal-Bench 2.0Gemini 3 Pro by 13.754.240.5+13.7
- SimpleVQAGemini 3 Pro by 11.469.758.3+11.4
- Artificial Analysis Coding IndexGemini 3 Pro by 9.546.537+9.5
- AA IntelligenceGemini 3 Pro by 8.72819.3+8.7
- HMMT Feb. 2025Gemini 3 Pro by 8.597.589+8.5
- VideoMMMUGemini 3 Pro by 7.287.680.4+7.2
- MMMLUGemini 3 Pro by 6.691.885.2+6.6
- MMVUGemini 3 Pro by 5.277.572.3+5.2
- MLVUQwen3.5 35B A3B by 4.980.785.6+4.9
- MMLU-ProGemini 3 Pro by 4.890.185.3+4.8
- t2-benchGemini 3 Pro by 4.285.481.2+4.2
- HMMT Nov. 2025Gemini 3 Pro by 4.193.389.2+4.1
- ScreenSpot-Pro (No tools)Gemini 3 Pro by 4.172.768.6+4.1
- Seal-0Gemini 3 Pro by 4.145.541.4+4.1
- vectara_factual_consistencyQwen3.5 35B A3B by 3.186.489.5+3.1
- MATH-VisionGemini 3 Pro by 2.286.183.9+2.2
- LVBenchGemini 3 Pro by 2.173.571.4+2.1
- OCRBench v2 (Chinese)Gemini 3 Pro by 2.163.861.7+2.1
- τ²-Bench Telecom (AA run)Qwen3.5 35B A3B by 2.187.189.2+2.1
- OmniDocBench 1.5tie88.589.3tie
- vectara_avg_summary_lengthtie101.994.9tie
- vectara_answer_ratetie99.499.8tie
- ZeroBenchtie88tie
Questions people ask
Which is better, Gemini 3 Pro or Qwen3.5 35B A3B?
Gemini 3 Pro wins five of the eight areas we test: coding, reasoning, images and charts, math and long documents. Qwen3.5 35B A3B wins agents and facts, and costs 84% less. They are level on following instructions.
Which is better for coding?
Gemini 3 Pro. It wins 6 of the 7 coding tests both models report; Qwen3.5 35B A3B wins 1.
Which is cheaper?
Gemini 3 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Qwen3.5 35B A3B costs $0.25 and $2.00. That makes Qwen3.5 35B A3B about 84% cheaper for the same work.
How do you compare the two?
We use the 53 benchmark tests both models have published scores on. The verdict counts the 28 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 25 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.