Gemini 3.5 Flash vs Qwen3.8 27B
Wins 3 of 8 areas
Reasoning · Images and charts · Math
Wins 3 of 8 areas
Coding · Agents · Long documents
The two are evenly matched.Gemini 3.5 Flash is better at reasoning and images and charts; Qwen3.8 27B at coding and agents.
Both rank among the ten best models we track in following instructions.
Scores updated · 35 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 thinking60Gemini 3.5 Flash6 of 6 tests
- Images and chartsUnderstanding pictures, charts and video21Gemini 3.5 Flash2 of 3 tests
- MathCompetition and research-level math10Gemini 3.5 Flash1 of 1 test
- CodingWriting and fixing software24Qwen3.8 27B4 of 6 tests
- AgentsCarrying out multi-step tasks on its own23Qwen3.8 27B3 of 5 tests
- Long documentsFinding answers in very long texts01Qwen3.8 27B1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
- Following instructionsDoing exactly what it is asked11Even1 each
Math and long documents rest on a single test 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.
Qwen3.8 27B costs 67% 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 3.5 Flash pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+35.8points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+29.7points ahead
- Common-sense trick questionsSimpleBench+16.5points ahead
Where Qwen3.8 27B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+31.9points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+15.8points ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+12.4points ahead
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.8 27B
- LiveBench · Agentic CodingQwen3.8 27B by 12.44961.4+12.4
- LMArena · WebDevQwen3.8 27B by 90 rating points15001590+90 rating
- SciCodeGemini 3.5 Flash by 7.353.946.6+7.3
- SWE-bench ProQwen3.8 27B by 6.655.161.7+6.6
- LiveBench · CodingGemini 3.5 Flash by 2.578.275.7+2.5
- Terminal-Bench 2.1Qwen3.8 27B by 1.178.779.8+1.1
AgentsQwen3.8 27B
- τ-Bench V3 · BankingQwen3.8 27B by 15.832.248+15.8
- GDPValQwen3.8 27B by 10.935.146+10.9
- MCP AtlasGemini 3.5 Flash by 6.383.677.3+6.3
- OSWorld-VerifiedQwen3.8 27B by 5.978.484.3+5.9
- Terminal-Bench 4.0Gemini 3.5 Flash by 16.65.6+1
ReasoningGemini 3.5 Flash
- ARC-AGI-2Gemini 3.5 Flash by 29.772.142.4+29.7
- SimpleBenchGemini 3.5 Flash by 16.576.760.2+16.5
- Humanity's Last ExamGemini 3.5 Flash by 8.842.733.9+8.8
- CritPtGemini 3.5 Flash by 7.713.15.4+7.7
- LiveBench · ReasoningGemini 3.5 Flash by 28280+2
- GPQA DiamondGemini 3.5 Flash by 1.792.290.5+1.7
FactsEven
- AA-Omniscience · AccuracyGemini 3.5 Flash by 35.851.415.6+35.8
- AA-Omniscience · Non-hallucinationQwen3.8 27B by 31.937.869.7+31.9
Images and chartsGemini 3.5 Flash
- MMMU-ProGemini 3.5 Flash by 884.376.3+8
- CharXiv (RQ)Qwen3.8 27B by 684.290.2+6
- LMArena · VisionGemini 3.5 Flash by 37 rating points13081271+37 rating
Following instructionsEven
- IFBenchQwen3.8 27B by 3.276.379.5+3.2
- LiveBench · Instruction FollowingGemini 3.5 Flash by 2.975.672.7+2.9
Other results9 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 3.5 Flash by 31.221.2-10+31.2
- AA Agentic IndexQwen3.8 27B by 19.227.346.5+19.2
- livebench_data_analysisQwen3.8 27B by 11.764.976.6+11.7
- livebench_languageGemini 3.5 Flash by 10.284.674.3+10.2
- DeepSWE 1.1Qwen3.8 27B by 5.23742.2+5.2
- ARC-AGI-1Gemini 3.5 Flash by 592.587.5+5
- LVBenchGemini 3.5 Flash by 3.976.372.4+3.9
- Artificial Analysis Coding IndexGemini 3.5 Flash by 270.168.1+2
- AA IntelligenceQwen3.8 27B by 1.132.633.7+1.1
Questions people ask
Which is better, Gemini 3.5 Flash or Qwen3.8 27B?
Gemini 3.5 Flash and Qwen3.8 27B each win three of the eight areas we test. Gemini 3.5 Flash wins reasoning, images and charts and math; Qwen3.8 27B wins coding, agents and long documents. Qwen3.8 27B costs 67% less. They are level on facts and following instructions.
Which is better for coding?
Qwen3.8 27B. It wins 4 of the 6 coding tests both models report; Gemini 3.5 Flash wins 2.
Which is cheaper?
Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens; Qwen3.8 27B costs $0.50 and $3.00. That makes Qwen3.8 27B about 67% cheaper for the same work.
How do you compare the two?
We use the 35 benchmark tests both models have published scores on. The verdict counts the 26 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.