Gemini 3.5 Flash vs Kimi K3
Wins 2 of 8 areas
Facts · Following instructions
Wins 5 of 8 areas
Coding · Agents · Reasoning · Math · Long documents
Kimi K3 is the stronger all-rounder.Gemini 3.5 Flash is cheaper and better at facts.
Scores updated · 43 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 software05Kimi K35 of 5 tests
- AgentsCarrying out multi-step tasks on its own15Kimi K35 of 7 tests · 1 tie
- MathCompetition and research-level math14Kimi K34 of 5 tests
- ReasoningHard problems that need careful thinking24Kimi K34 of 6 tests
- Long documentsFinding answers in very long texts01Kimi K31 of 1 test
- FactsGetting facts right instead of making them up21Gemini 3.5 Flash2 of 3 tests
- Following instructionsDoing exactly what it is asked10Gemini 3.5 Flash1 of 1 test
- Images and chartsUnderstanding pictures, charts and video11Even1 each
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.
Gemini 3.5 Flash costs 42% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Kimi K3 pulls ahead
- Real work tasks from 44 professionsGDPVal+16.5points ahead
- Reasons across sets of long documentsAA-LCR+15.4points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+13.8points ahead
Where Gemini 3.5 Flash pulls ahead
- Common-sense trick questionsSimpleBench+16points ahead
- Short factual questions, answered correctlySimpleQA Verified+15.6points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+11.7points ahead
Every test, side by side
All 43 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi K3
- LMArena · WebDevKimi K3 by 156 rating points14991655+156 rating
- LiveBench · Agentic CodingKimi K3 by 13.24962.2+13.2
- Terminal-Bench 2.1Kimi K3 by 6.378.785+6.3
- SciCodeKimi K3 by 5.653.959.5+5.6
- LiveBench · CodingKimi K3 by 3.378.281.5+3.3
AgentsKimi K3
- GDPValKimi K3 by 16.535.251.7+16.5
- τ-Bench V3 · BankingKimi K3 by 13.832.246+13.8
- AA IT-Bench SREKimi K3 by 7.440.347.7+7.4
- OSWorld-VerifiedKimi K3 by 6.478.484.8+6.4
- Terminal-Bench 4.0Kimi K3 by 66.612.6+6
- AA ApexAgentsGemini 3.5 Flash by 5.847.141.3+5.8
- MCP Atlastie83.684.2tie
ReasoningKimi K3
- SimpleBenchGemini 3.5 Flash by 1676.760.7+16
- ARC-AGI-2Gemini 3.5 Flash by 11.772.160.4+11.7
- CritPtKimi K3 by 10.313.123.4+10.3
- LiveBench · ReasoningKimi K3 by 8.78290.7+8.7
- Humanity's Last ExamKimi K3 by 4.242.746.9+4.2
- GPQA DiamondKimi K3 by 1.392.293.5+1.3
FactsGemini 3.5 Flash
- SimpleQA VerifiedGemini 3.5 Flash by 15.666.250.6+15.6
- AA-Omniscience · Non-hallucinationKimi K3 by 937.846.8+9
- AA-Omniscience · AccuracyGemini 3.5 Flash by 3.851.447.6+3.8
Images and chartsEven
- CharXiv (RQ)Kimi K3 by 7.184.291.3+7.1
- MMMU-ProGemini 3.5 Flash by 3.884.380.5+3.8
MathKimi K3
- FrontierMath Tier 4Kimi K3 by 12.226.839+12.2
- FrontierMath Tiers 1-3 (v2)Kimi K3 by 9.462.872.2+9.4
- LiveBench · MathematicsGemini 3.5 Flash by 3.888.284.4+3.8
- AIME 2026Kimi K3 by 1.79596.7+1.7
- HMMT Feb. 2026Kimi K3 by 1.595.597+1.5
Following instructionsGemini 3.5 Flash
- LiveBench · Instruction FollowingGemini 3.5 Flash by 4.275.671.4+4.2
Other results13 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 v2 EloKimi K3 by 337 rating points13491686+337 rating
- GDPval-AA v2Kimi K3 by 333 rating points13491682+333 rating
- DeepSWE 1.1Kimi K3 by 323769+32
- DeepSWEKimi K3 by 30.53767.5+30.5
- AA Agentic IndexKimi K3 by 23.327.350.6+23.3
- ToolathlonKimi K3 by 16.756.573.2+16.7
- livebench_data_analysisKimi K3 by 13.864.978.7+13.8
- AA IntelligenceKimi K3 by 1132.643.6+11
- Artificial Analysis Coding IndexKimi K3 by 6.170.176.2+6.1
- ARC-AGI-1Kimi K3 by 292.594.5+2
- AA-OmniscienceGemini 3.5 Flash by 1.521.219.7+1.5
- matharena_visual_math_overallKimi K3 by 1.489.991.3+1.4
- livebench_languagetie84.685.5tie
Questions people ask
Which is better, Gemini 3.5 Flash or Kimi K3?
Kimi K3 wins five of the eight areas we test: coding, agents, reasoning, math and long documents. Gemini 3.5 Flash wins facts and following instructions, and costs 42% less. They are level on images and charts.
Which is better for coding?
Kimi K3. It wins 5 of the 5 coding tests both models report; Gemini 3.5 Flash wins none.
Which is cheaper?
Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens; Kimi K3 costs $3.00 and $15.00. That makes Gemini 3.5 Flash about 42% cheaper for the same work.
How do you compare the two?
We use the 43 benchmark tests both models have published scores on. The verdict counts the 30 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.