Gemini 2.5 Pro vs Qwen3.5 397B A17B
Wins 1 of 8 areas
Facts
Wins 7 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math · Long documents · Following instructions
Qwen3.5 397B A17B is the stronger all-rounder.Gemini 2.5 Pro is better at facts.
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 software14Qwen3.5 397B A17B4 of 5 tests
- AgentsCarrying out multi-step tasks on its own03Qwen3.5 397B A17B3 of 4 tests · 1 tie
- ReasoningHard problems that need careful thinking02Qwen3.5 397B A17B2 of 3 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video02Qwen3.5 397B A17B2 of 3 tests · 1 tie
- Long documentsFinding answers in very long texts02Qwen3.5 397B A17B2 of 2 tests
- Following instructionsDoing exactly what it is asked02Qwen3.5 397B A17B2 of 2 tests
- MathCompetition and research-level math01Qwen3.5 397B A17B1 of 1 test
- FactsGetting facts right instead of making them up21Gemini 2.5 Pro2 of 3 tests
Math 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 397B A17B costs 63% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.5 397B A17B pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+59.1points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+30.1points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+22.8points ahead
Where Gemini 2.5 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+30points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+8.3points ahead
- Code for real scientific research problemsSciCode+1.5points 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.
CodingQwen3.5 397B A17B
- Terminal-Bench 2.1Qwen3.5 397B A17B by 22.828.551.3+22.8
- LMArena · WebDevQwen3.5 397B A17B by 176 rating points12241400+176 rating
- Terminal-Bench HardQwen3.5 397B A17B by 14.426.540.9+14.4
- SWE-bench VerifiedQwen3.5 397B A17B by 13.263.276.4+13.2
- SciCodeGemini 2.5 Pro by 1.546.344.8+1.5
AgentsQwen3.5 397B A17B
- BrowseCompQwen3.5 397B A17B by 59.19.969+59.1
- GDPValQwen3.5 397B A17B by 14.8014.8+14.8
- τ-Bench V3 · BankingQwen3.5 397B A17B by 3.79.713.4+3.7
- Terminal-Bench 4.0tie00tie
ReasoningQwen3.5 397B A17B
- Humanity's Last ExamQwen3.5 397B A17B by 111829+11
- GPQA DiamondQwen3.5 397B A17B by 5.783.689.3+5.7
- CritPttie2.61.7tie
FactsGemini 2.5 Pro
- SimpleQA VerifiedGemini 2.5 Pro by 305626+30
- AA-Omniscience · AccuracyGemini 2.5 Pro by 8.33930.8+8.3
- AA-Omniscience · Non-hallucinationQwen3.5 397B A17B by 29.111.1+2
Images and chartsQwen3.5 397B A17B
- MMMUQwen3.5 397B A17B by 5.479.685+5.4
- MMMU-ProQwen3.5 397B A17B by 2.474.977.3+2.4
- LMArena · Visiontie12631264tie
MathQwen3.5 397B A17B
- FrontierMath Tiers 1-3 (v2)Qwen3.5 397B A17B by 6.624.631.2+6.6
Long documentsQwen3.5 397B A17B
- AA-LCRQwen3.5 397B A17B by 8.36977.3+8.3
- LongBench v2Qwen3.5 397B A17B by 4.458.863.2+4.4
Following instructionsQwen3.5 397B A17B
- IFBenchQwen3.5 397B A17B by 30.148.778.8+30.1
- Multi-ChallengeQwen3.5 397B A17B by 1453.667.6+14
Other results11 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.
- τ²-Bench Telecom (AA run)Qwen3.5 397B A17B by 41.554.195.6+41.5
- BrowseComp-ZHQwen3.5 397B A17B by 38.132.270.3+38.1
- HMMT 2025Qwen3.5 397B A17B by 2765.792.7+27
- HLE (with tools)Qwen3.5 397B A17B by 19.928.448.3+19.9
- AA-OmniscienceGemini 2.5 Pro by 14.4-16.4-30.8+14.4
- HMMT Feb. 2025Qwen3.5 397B A17B by 1480.894.8+14
- HMMT Nov. 2025Qwen3.5 397B A17B by 12.78092.7+12.7
- AA Agentic IndexQwen3.5 397B A17B by 7.13.510.6+7.1
- AA IntelligenceQwen3.5 397B A17B by 3.41518.4+3.4
- MMLU-ProQwen3.5 397B A17B by 1.88687.8+1.8
- Artificial Analysis Coding IndexQwen3.5 397B A17B by 1.546.748.2+1.5
Questions people ask
Which is better, Gemini 2.5 Pro or Qwen3.5 397B A17B?
Qwen3.5 397B A17B wins seven of the eight areas we test: coding, agents, reasoning, images and charts, math, long documents and following instructions. Gemini 2.5 Pro wins facts.
Which is better for coding?
Qwen3.5 397B A17B. It wins 4 of the 5 coding tests both models report; Gemini 2.5 Pro wins 1.
Which is cheaper?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; Qwen3.5 397B A17B costs $0.60 and $3.60. That makes Qwen3.5 397B A17B about 63% 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 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 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.