Claude Sonnet 4.6 vs Kimi K3
Wins 1 of 8 areas
Math
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents · Following instructions
Kimi K3 is the stronger all-rounder.Claude Sonnet 4.6 is better at math.
Scores updated · 38 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 own08Kimi K38 of 8 tests
- CodingWriting and fixing software05Kimi K35 of 5 tests
- ReasoningHard problems that need careful thinking05Kimi K35 of 5 tests
- Images and chartsUnderstanding pictures, charts and video02Kimi K32 of 2 tests
- FactsGetting facts right instead of making them up12Kimi K32 of 3 tests
- Long documentsFinding answers in very long texts01Kimi K31 of 1 test
- Following instructionsDoing exactly what it is asked01Kimi K31 of 1 test
- MathCompetition and research-level math10Claude Sonnet 4.61 of 1 test
Math, 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Kimi K3 pulls ahead
- Multi-step tasks using many real software toolsMCP Atlas+22.9points ahead
- Research-level physics problemsCritPt+20.3points ahead
- Reasoning about charts from research papersCharXiv (RQ)+19.7points ahead
Where Claude Sonnet 4.6 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+4.8points ahead
- Fresh competition math problemsLiveBench · Mathematics+2.6points ahead
Every test, side by side
All 38 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi K3
- LiveBench · Agentic CodingKimi K3 by 19.642.662.2+19.6
- Terminal-Bench 2.1Kimi K3 by 13.871.285+13.8
- LMArena · WebDevKimi K3 by 133 rating points15221655+133 rating
- SciCodeKimi K3 by 9.450.159.5+9.4
- LiveBench · CodingKimi K3 by 2.279.381.5+2.2
AgentsKimi K3
- MCP AtlasKimi K3 by 22.961.384.2+22.9
- BrowseCompKimi K3 by 16.574.791.2+16.5
- GDPValKimi K3 by 1536.751.7+15
- AA ApexAgentsKimi K3 by 13.32841.3+13.3
- OSWorld-VerifiedKimi K3 by 12.372.584.8+12.3
- τ-Bench V3 · BankingKimi K3 by 11.634.446+11.6
- Terminal-Bench 4.0Kimi K3 by 9.6312.6+9.6
- AA IT-Bench SREKimi K3 by 7.939.847.7+7.9
ReasoningKimi K3
- CritPtKimi K3 by 20.33.123.4+20.3
- Humanity's Last ExamKimi K3 by 13.333.646.9+13.3
- GPQA DiamondKimi K3 by 687.593.5+6
- LiveBench · ReasoningKimi K3 by 5.984.890.7+5.9
- ARC-AGI-2Kimi K3 by 2.158.360.4+2.1
FactsKimi K3
- SimpleQA VerifiedKimi K3 by 17.832.850.6+17.8
- AA-Omniscience · AccuracyKimi K3 by 6.740.947.6+6.7
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.6 by 4.851.646.8+4.8
Images and chartsKimi K3
- CharXiv (RQ)Kimi K3 by 19.771.691.3+19.7
- MMMU-ProKimi K3 by 7.273.380.5+7.2
Following instructionsKimi K3
- LiveBench · Instruction FollowingKimi K3 by 8.263.271.4+8.2
Other results12 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.
- DeepSWE 1.1Kimi K3 by 393069+39
- ToolathlonKimi K3 by 32.24173.2+32.2
- GDPval-AA v2Kimi K3 by 287 rating points13951682+287 rating
- AA Agentic IndexKimi K3 by 17.533.150.6+17.5
- AA IntelligenceKimi K3 by 13.530.143.6+13.5
- Artificial Analysis Coding IndexKimi K3 by 13.26376.2+13.2
- HLE (with tools)Kimi K3 by 1346.859.8+13
- OfficeQA ProKimi K3 by 9.953.463.3+9.9
- livebench_languageKimi K3 by 9.476.185.5+9.4
- ARC-AGI-1Kimi K3 by 8.58694.5+8.5
- AA-OmniscienceKimi K3 by 7.512.219.7+7.5
- livebench_data_analysistie7878.7tie
Questions people ask
Which is better, Claude Sonnet 4.6 or Kimi K3?
Kimi K3 wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, long documents and following instructions. Claude Sonnet 4.6 wins math.
Which is better for coding?
Kimi K3. It wins 5 of the 5 coding tests both models report; Claude Sonnet 4.6 wins none.
Which is cheaper?
Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; Kimi K3 costs $3.00 and $15.00. For a million tokens read plus a million written, they cost about the same.
How do you compare the two?
We use the 38 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 12 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.