Gemini 3.5 Flash vs Kimi K2.5
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Following instructions
Wins 1 of 8 areas
Long documents
Gemini 3.5 Flash is the stronger all-rounder.Kimi K2.5 is cheaper and better at long documents.
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.
- CodingWriting and fixing software50Gemini 3.5 Flash5 of 5 tests
- AgentsCarrying out multi-step tasks on its own50Gemini 3.5 Flash5 of 5 tests
- ReasoningHard problems that need careful thinking40Gemini 3.5 Flash4 of 4 tests
- Images and chartsUnderstanding pictures, charts and video30Gemini 3.5 Flash3 of 4 tests · 1 tie
- FactsGetting facts right instead of making them up30Gemini 3.5 Flash3 of 3 tests
- MathCompetition and research-level math10Gemini 3.5 Flash1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked10Gemini 3.5 Flash1 of 1 test
- Long documentsFinding answers in very long texts01Kimi K2.51 of 1 test
Long documents and following instructions 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.
Kimi K2.5 costs 66% 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 3.5 Flash pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+60.3points ahead
- Long professional tasks in banking, consulting and lawAA ApexAgents+35.6points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+33points ahead
Where Kimi K2.5 pulls ahead
- Reasons across sets of long documentsAA-LCR+4.7points 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 3.5 Flash
- Terminal-Bench 2.1Gemini 3.5 Flash by 3378.745.7+33
- LMArena · WebDevGemini 3.5 Flash by 63 rating points14991436+63 rating
- Terminal-Bench HardGemini 3.5 Flash by 6.140.934.8+6.1
- SciCodeGemini 3.5 Flash by 4.953.949+4.9
- SWE-bench ProGemini 3.5 Flash by 4.455.150.7+4.4
AgentsGemini 3.5 Flash
- AA ApexAgentsGemini 3.5 Flash by 35.647.111.5+35.6
- MCP AtlasGemini 3.5 Flash by 19.883.663.8+19.8
- GDPValGemini 3.5 Flash by 1835.217.2+18
- τ-Bench V3 · BankingGemini 3.5 Flash by 1832.214.2+18
- OSWorld-VerifiedGemini 3.5 Flash by 15.178.463.3+15.1
ReasoningGemini 3.5 Flash
- ARC-AGI-2Gemini 3.5 Flash by 60.372.111.8+60.3
- Humanity's Last ExamGemini 3.5 Flash by 1242.730.7+12
- CritPtGemini 3.5 Flash by 1013.13.1+10
- GPQA DiamondGemini 3.5 Flash by 4.392.287.9+4.3
FactsGemini 3.5 Flash
- SimpleQA VerifiedGemini 3.5 Flash by 31.966.234.3+31.9
- AA-Omniscience · AccuracyGemini 3.5 Flash by 16.251.435.2+16.2
- AA-Omniscience · Non-hallucinationGemini 3.5 Flash by 3.537.834.3+3.5
Images and chartsGemini 3.5 Flash
- MMMU-ProGemini 3.5 Flash by 8.984.375.4+8.9
- CharXiv (RQ)Gemini 3.5 Flash by 6.784.277.5+6.7
- LMArena · VisionGemini 3.5 Flash by 41 rating points13101269+41 rating
- Video-MMEtie87.287.4tie
MathGemini 3.5 Flash
- HMMT Feb. 2026Gemini 3.5 Flash by 8.495.587.1+8.4
- AIME 2026tie9595.8tie
Following instructionsGemini 3.5 Flash
- IFBenchGemini 3.5 Flash by 6.176.370.2+6.1
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.
- GDPval-AA v2Gemini 3.5 Flash by 340 rating points13491009+340 rating
- ToolathlonGemini 3.5 Flash by 28.756.527.8+28.7
- AA-OmniscienceGemini 3.5 Flash by 28.521.2-7.3+28.5
- ARC-AGI-1Gemini 3.5 Flash by 27.292.565.3+27.2
- Terminal-Bench 2.0Gemini 3.5 Flash by 25.476.250.8+25.4
- Artificial Analysis Coding IndexGemini 3.5 Flash by 23.370.146.8+23.3
- frontiermath_tier_4_v1Gemini 3.5 Flash by 10.414.64.2+10.4
- matharena_visual_math_overallGemini 3.5 Flash by 9.389.980.6+9.3
- AA IntelligenceGemini 3.5 Flash by 9.132.623.5+9.1
- LiveBenchGemini 3.5 Flash by 5.97569.1+5.9
- AA Agentic IndexGemini 3.5 Flash by 5.627.321.7+5.6
- LongVideoBenchKimi K2.5 by 2.277.679.8+2.2
- τ²-Bench Telecom (AA run)tie95.395.9tie
- LVBenchtie76.375.9tie
- MotionBenchtie70.670.4tie
Questions people ask
Which is better, Gemini 3.5 Flash or Kimi K2.5?
Gemini 3.5 Flash wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and following instructions. Kimi K2.5 wins long documents, and costs 66% less.
Which is better for coding?
Gemini 3.5 Flash. It wins 5 of the 5 coding tests both models report; Kimi K2.5 wins none.
Which is cheaper?
Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens; Kimi K2.5 costs $0.60 and $3.00. That makes Kimi K2.5 about 66% 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.