Gemini 3.5 Flash vs Kimi K2.6
Wins 6 of 8 areas
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 K2.6 is cheaper and better at long documents.
Scores updated · 47 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.
- AgentsCarrying out multi-step tasks on its own70Gemini 3.5 Flash7 of 7 tests
- ReasoningHard problems that need careful thinking40Gemini 3.5 Flash4 of 4 tests
- MathCompetition and research-level math41Gemini 3.5 Flash4 of 5 tests
- FactsGetting facts right instead of making them up21Gemini 3.5 Flash2 of 3 tests
- Images and chartsUnderstanding pictures, charts and video21Gemini 3.5 Flash2 of 3 tests
- Following instructionsDoing exactly what it is asked10Gemini 3.5 Flash1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01Kimi K2.61 of 1 test
- CodingWriting and fixing software33Even3 each · 1 tie
Long documents 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.
Kimi K2.6 costs 53% 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
- Short factual questions, answered correctlySimpleQA Verified+31.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+18.8points ahead
- Long professional tasks in banking, consulting and lawAA ApexAgents+18.6points ahead
Where Kimi K2.6 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+21.7points ahead
- Reasons across sets of long documentsAA-LCR+7.7points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+3.5points ahead
Every test, side by side
All 47 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- Terminal-Bench 2.1Gemini 3.5 Flash by 12.878.765.9+12.8
- SWE-bench ProKimi K2.6 by 3.555.158.6+3.5
- Terminal-Bench HardKimi K2.6 by 340.943.9+3
- SciCodeGemini 3.5 Flash by 2.453.951.5+2.4
- LiveBench · Agentic CodingGemini 3.5 Flash by 2.14946.9+2.1
- LMArena · WebDevKimi K2.6 by 10 rating points14991509+10 rating
- LiveBench · Codingtie78.278.6tie
AgentsGemini 3.5 Flash
- AA ApexAgentsGemini 3.5 Flash by 18.647.128.5+18.6
- MCP AtlasGemini 3.5 Flash by 15.583.668.1+15.5
- AA IT-Bench SREGemini 3.5 Flash by 9.140.331.2+9.1
- τ-Bench V3 · BankingGemini 3.5 Flash by 8.932.223.3+8.9
- GDPValGemini 3.5 Flash by 8.235.227+8.2
- Terminal-Bench 4.0Gemini 3.5 Flash by 6.16.60.5+6.1
- OSWorld-VerifiedGemini 3.5 Flash by 5.378.473.1+5.3
ReasoningGemini 3.5 Flash
- Humanity's Last ExamGemini 3.5 Flash by 5.242.737.5+5.2
- CritPtGemini 3.5 Flash by 5.113.18+5.1
- LiveBench · ReasoningGemini 3.5 Flash by 2.68279.4+2.6
- GPQA DiamondGemini 3.5 Flash by 1.192.291.1+1.1
FactsGemini 3.5 Flash
- SimpleQA VerifiedGemini 3.5 Flash by 31.366.234.9+31.3
- AA-Omniscience · Non-hallucinationKimi K2.6 by 21.737.859.5+21.7
- AA-Omniscience · AccuracyGemini 3.5 Flash by 18.851.432.6+18.8
Images and chartsGemini 3.5 Flash
- MMMU-ProGemini 3.5 Flash by 4.984.379.4+4.9
- LMArena · VisionGemini 3.5 Flash by 28 rating points13101282+28 rating
- CharXiv (RQ)Kimi K2.6 by 2.584.286.7+2.5
MathGemini 3.5 Flash
- FrontierMath Tiers 1-3 (v2)Gemini 3.5 Flash by 5.662.857.2+5.6
- LiveBench · MathematicsGemini 3.5 Flash by 3.988.284.3+3.9
- HMMT Feb. 2026Gemini 3.5 Flash by 2.895.592.7+2.8
- AIME 2026Kimi K2.6 by 1.49596.4+1.4
- FrontierMath Tier 4Gemini 3.5 Flash by 1.226.825.6+1.2
Following instructionsGemini 3.5 Flash
- LiveBench · Instruction FollowingGemini 3.5 Flash by 11.275.664.4+11.2
- IFBenchtie76.376tie
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 (Elo)Gemini 3.5 Flash by 174 rating points16561482+174 rating
- AA-OmniscienceGemini 3.5 Flash by 15.921.25.3+15.9
- GDPval-AA v2Gemini 3.5 Flash by 159 rating points13491190+159 rating
- Finance Agent v2Gemini 3.5 Flash by 1357.944.9+13
- livebench_languageGemini 3.5 Flash by 9.584.675.1+9.5
- Terminal-Bench 2.0Gemini 3.5 Flash by 9.576.266.7+9.5
- HiL-Bench (Tools-allowed)Gemini 3.5 Flash by 927.718.7+9
- Artificial Analysis Coding IndexGemini 3.5 Flash by 8.370.161.8+8.3
- ToolathlonGemini 3.5 Flash by 6.556.550+6.5
- AA IntelligenceGemini 3.5 Flash by 5.632.627+5.6
- AA Agentic IndexGemini 3.5 Flash by 5.227.322.1+5.2
- LiveBenchGemini 3.5 Flash by 2.87572.2+2.8
- τ²-Bench Telecom (AA run)tie95.395.9tie
- livebench_data_analysistie64.965.1tie
- frontiermath_tier_4_v1tie14.614.6tie
Questions people ask
Which is better, Gemini 3.5 Flash or Kimi K2.6?
Gemini 3.5 Flash wins six of the eight areas we test: agents, reasoning, facts, images and charts, math and following instructions. Kimi K2.6 wins long documents, and costs 53% less. They are level on coding.
Which is better for coding?
Neither. They win 3 coding tests each of the 7 both models report, and 1 is a tie.
Which is cheaper?
Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens; Kimi K2.6 costs $0.95 and $4.00. That makes Kimi K2.6 about 53% cheaper for the same work.
How do you compare the two?
We use the 47 benchmark tests both models have published scores on. The verdict counts the 32 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.