Gemini 3 Pro vs Qwen3.5 9B
Wins 7 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
Gemini 3 Pro is the stronger all-rounder.Qwen3.5 9B is cheaper.
Scores updated · 34 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 software30Gemini 3 Pro3 of 3 tests
- ReasoningHard problems that need careful thinking30Gemini 3 Pro3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20Gemini 3 Pro2 of 2 tests
- Long documentsFinding answers in very long texts20Gemini 3 Pro2 of 2 tests
- Following instructionsDoing exactly what it is asked20Gemini 3 Pro2 of 2 tests
- MathCompetition and research-level math10Gemini 3 Pro1 of 2 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own10Gemini 3 Pro1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Agents 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.
Qwen3.5 9B costs 98% 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 Gemini 3 Pro pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+39.4points ahead
- Code for real scientific research problemsSciCode+26.6points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+24.8points ahead
Where Qwen3.5 9B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+7.9points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3 Pro
- SciCodeGemini 3 Pro by 26.656.129.5+26.6
- LiveCodeBench v6Gemini 3 Pro by 21.887.465.6+21.8
- Terminal-Bench HardGemini 3 Pro by 17.541.724.2+17.5
ReasoningGemini 3 Pro
- Humanity's Last ExamGemini 3 Pro by 24.839.714.9+24.8
- GPQA DiamondGemini 3 Pro by 10.290.880.6+10.2
- CritPtGemini 3 Pro by 8.89.10.3+8.8
FactsEven
- AA-Omniscience · AccuracyGemini 3 Pro by 39.455.816.4+39.4
- AA-Omniscience · Non-hallucinationQwen3.5 9B by 7.98.516.4+7.9
Images and chartsGemini 3 Pro
- MMMU-ProGemini 3 Pro by 1180.269.2+11
- OCRBenchv2Gemini 3 Pro by 4.763.458.7+4.7
MathGemini 3 Pro
- HMMT Feb. 2026Gemini 3 Pro by 15.286.471.2+15.2
- AIME 2026tie91.792.5tie
Long documentsGemini 3 Pro
- LongBench v2Gemini 3 Pro by 1368.255.2+13
- AA-LCRGemini 3 Pro by 67670+6
Following instructionsGemini 3 Pro
- Multi-ChallengeGemini 3 Pro by 11.265.754.5+11.2
- IFBenchGemini 3 Pro by 3.770.466.7+3.7
Other results17 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 68.815.3-53.5+68.8
- AA Agentic IndexGemini 3 Pro by 45527+45
- AIME25 no toolsGemini 3 Pro by 39.99656.1+39.9
- MLVUGemini 3 Pro by 28.380.752.4+28.3
- Artificial Analysis Coding IndexGemini 3 Pro by 17.846.528.7+17.8
- AA IntelligenceGemini 3 Pro by 16.82811.2+16.8
- RefCOCO-AQwen3.5 9B by 12.181.593.6+12.1
- VideoHallucerGemini 3 Pro by 10.866.856+10.8
- MMMLUGemini 3 Pro by 10.691.881.2+10.6
- MMVUGemini 3 Pro by 8.977.568.6+8.9
- MMLU-ProGemini 3 Pro by 7.690.182.5+7.6
- VQA-V2Gemini 3 Pro by 6.689.883.2+6.6
- t2-benchGemini 3 Pro by 6.385.479.1+6.3
- RefCOCO-BQwen3.5 9B by 5.982.888.8+5.9
- Mobile ActionsQwen3.5 9B by 2.489.491.8+2.4
- OCRBench v2 (Chinese)tie63.864.1tie
- τ²-Bench Telecom (AA run)tie87.186.8tie
Questions people ask
Which is better, Gemini 3 Pro or Qwen3.5 9B?
Gemini 3 Pro wins seven of the eight areas we test: coding, agents, reasoning, images and charts, math, long documents and following instructions. Qwen3.5 9B wins none, but costs 98% less. They are level on facts.
Which is better for coding?
Gemini 3 Pro. It wins 3 of the 3 coding tests both models report; Qwen3.5 9B wins none.
Which is cheaper?
Gemini 3 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Qwen3.5 9B costs $0.14 and $0.20. That makes Qwen3.5 9B about 98% cheaper for the same work.
How do you compare the two?
We use the 34 benchmark tests both models have published scores on. The verdict counts the 17 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 17 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.