Gemini 3 Pro vs Qwen3.5 397B A17B
Wins 5 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts
Wins 1 of 8 areas
Following instructions
Gemini 3 Pro is the stronger all-rounder.Qwen3.5 397B A17B is cheaper and better at following instructions.
Scores updated · 40 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.
- ReasoningHard problems that need careful thinking30Gemini 3 Pro3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20Gemini 3 Pro2 of 2 tests
- CodingWriting and fixing software32Gemini 3 Pro3 of 7 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own21Gemini 3 Pro2 of 3 tests
- FactsGetting facts right instead of making them up21Gemini 3 Pro2 of 3 tests
- Following instructionsDoing exactly what it is asked02Qwen3.5 397B A17B2 of 2 tests
- MathCompetition and research-level math11Even1 each · 1 tie
- Long documentsFinding answers in very long texts11Even1 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 397B A17B costs 70% 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
- Short factual questions, answered correctlySimpleQA Verified+46.9points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+25points ahead
- Real work tasks from 44 professionsGDPVal+19.4points ahead
Where Qwen3.5 397B A17B pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+9.8points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+8.4points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+7.6points ahead
Every test, side by side
All 40 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 11.356.144.8+11.3
- SWE-bench ProQwen3.5 397B A17B by 7.643.350.9+7.6
- SWE-bench MultilingualQwen3.5 397B A17B by 4.36569.3+4.3
- LMArena · WebDevGemini 3 Pro by 40 rating points14401400+40 rating
- LiveCodeBench v6Gemini 3 Pro by 3.887.483.6+3.8
- Terminal-Bench Hardtie41.740.9tie
- SWE-bench Verifiedtie76.276.4tie
AgentsGemini 3 Pro
- GDPValGemini 3 Pro by 19.434.214.8+19.4
- BrowseCompQwen3.5 397B A17B by 9.859.269+9.8
- AA ApexAgentsGemini 3 Pro by 3.118.415.3+3.1
ReasoningGemini 3 Pro
- Humanity's Last ExamGemini 3 Pro by 10.739.729+10.7
- CritPtGemini 3 Pro by 7.49.11.7+7.4
- GPQA DiamondGemini 3 Pro by 1.590.889.3+1.5
FactsGemini 3 Pro
- SimpleQA VerifiedGemini 3 Pro by 46.972.926+46.9
- AA-Omniscience · AccuracyGemini 3 Pro by 2555.830.8+25
- AA-Omniscience · Non-hallucinationQwen3.5 397B A17B by 2.68.511.1+2.6
Images and chartsGemini 3 Pro
- LMArena · VisionGemini 3 Pro by 41 rating points13051264+41 rating
- MMMU-ProGemini 3 Pro by 2.980.277.3+2.9
MathEven
- IMOAnswerBenchGemini 3 Pro by 2.283.180.9+2.2
- HMMT Feb. 2026Qwen3.5 397B A17B by 1.586.487.9+1.5
- AIME 2026tie91.791.3tie
Long documentsEven
- LongBench v2Gemini 3 Pro by 568.263.2+5
- AA-LCRQwen3.5 397B A17B by 1.37677.3+1.3
Following instructionsQwen3.5 397B A17B
- IFBenchQwen3.5 397B A17B by 8.470.478.8+8.4
- Multi-ChallengeQwen3.5 397B A17B by 1.965.767.6+1.9
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-OmniscienceGemini 3 Pro by 4615.3-30.8+46
- AA Agentic IndexGemini 3 Pro by 41.45210.6+41.4
- BrowseComp (context management)Qwen3.5 397B A17B by 19.459.278.6+19.4
- AA IntelligenceGemini 3 Pro by 9.62818.4+9.6
- τ²-Bench Telecom (AA run)Qwen3.5 397B A17B by 8.587.195.6+8.5
- MMMLUGemini 3 Pro by 3.391.888.5+3.3
- HMMT Feb. 2025Gemini 3 Pro by 2.797.594.8+2.7
- HLE (with tools)Qwen3.5 397B A17B by 2.545.848.3+2.5
- MMLU-ProGemini 3 Pro by 2.390.187.8+2.3
- ToolathlonQwen3.5 397B A17B by 1.936.438.3+1.9
- Artificial Analysis Coding IndexQwen3.5 397B A17B by 1.746.548.2+1.7
- Terminal-Bench 2.0Gemini 3 Pro by 1.754.252.5+1.7
- Seal-0Qwen3.5 397B A17B by 1.445.546.9+1.4
- t2-benchQwen3.5 397B A17B by 1.385.486.7+1.3
- HMMT Nov. 2025tie93.392.7tie
Questions people ask
Which is better, Gemini 3 Pro or Qwen3.5 397B A17B?
Gemini 3 Pro wins five of the eight areas we test: coding, agents, reasoning, facts and images and charts. Qwen3.5 397B A17B wins following instructions, and costs 70% less. They are level on math and long documents.
Which is better for coding?
Gemini 3 Pro. It wins 3 of the 7 coding tests both models report; Qwen3.5 397B A17B wins 2, and 2 are ties.
Which is cheaper?
Gemini 3 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Qwen3.5 397B A17B costs $0.60 and $3.60. That makes Qwen3.5 397B A17B about 70% cheaper for the same work.
How do you compare the two?
We use the 40 benchmark tests both models have published scores on. The verdict counts the 25 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.