Claude Sonnet 5 vs Kimi K3
Wins 0 of 8 areas
—
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Kimi K3 is the stronger all-rounder.Claude Sonnet 5 is cheaper.
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 software04Kimi K34 of 5 tests · 1 tie
- ReasoningHard problems that need careful thinking04Kimi K34 of 5 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own14Kimi K34 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
- MathCompetition and research-level math12Kimi 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
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.
Claude Sonnet 5 costs 33% 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
- Short factual questions, answered correctlySimpleQA Verified+16.9points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+9.7points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+8.7points ahead
Where Claude Sonnet 5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+13.8points ahead
- Fresh competition math problemsLiveBench · Mathematics+8.5points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+1.5points 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.
CodingKimi K3
- LMArena · WebDevKimi K3 by 119 rating points15391658+119 rating
- SciCodeKimi K3 by 5.254.359.5+5.2
- Terminal-Bench 2.1Kimi K3 by 4.580.585+4.5
- LiveBench · Agentic CodingKimi K3 by 2.859.462.2+2.8
- LiveBench · Codingtie80.781.5tie
AgentsKimi K3
- τ-Bench V3 · BankingKimi K3 by 8.737.346+8.7
- BrowseCompKimi K3 by 6.584.791.2+6.5
- OSWorld-VerifiedKimi K3 by 3.681.284.8+3.6
- GDPValKimi K3 by 3.548.351.8+3.5
- Terminal-Bench 4.0Claude Sonnet 5 by 1.514.112.6+1.5
ReasoningKimi K3
- CritPtKimi K3 by 6.516.923.4+6.5
- Humanity's Last ExamKimi K3 by 5.641.346.9+5.6
- GPQA DiamondKimi K3 by 2.491.193.5+2.4
- LiveBench · ReasoningKimi K3 by 288.790.7+2
- SimpleBenchtie60.660.7tie
FactsKimi K3
- SimpleQA VerifiedKimi K3 by 16.933.750.6+16.9
- AA-Omniscience · Non-hallucinationClaude Sonnet 5 by 13.860.646.8+13.8
- AA-Omniscience · AccuracyKimi K3 by 7.54047.6+7.5
Images and chartsKimi K3
- MMMU-ProKimi K3 by 3.277.380.5+3.2
- CharXiv (RQ)Kimi K3 by 388.391.3+3
MathKimi K3
- FrontierMath Tier 4Kimi K3 by 9.729.339+9.7
- LiveBench · MathematicsClaude Sonnet 5 by 8.592.984.4+8.5
- FrontierMath Tiers 1-3 (v2)Kimi K3 by 6.665.672.2+6.6
Following instructionsKimi K3
- LiveBench · Instruction FollowingKimi K3 by 7.563.971.4+7.5
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.
- ToolathlonKimi K3 by 18.954.373.2+18.9
- DeepSWE 1.1Kimi K3 by 155469+15
- livebench_languageKimi K3 by 10.57585.5+10.5
- GDPval-AA v2 EloKimi K3 by 102 rating points15841686+102 rating
- livebench_data_analysisKimi K3 by 771.778.7+7
- GDPval-AA v2Kimi K3 by 64 rating points16181682+64 rating
- AA Agentic IndexKimi K3 by 6.344.350.6+6.3
- AA IntelligenceKimi K3 by 5.438.243.6+5.4
- Artificial Analysis Coding IndexKimi K3 by 4.771.576.2+4.7
- OfficeQA ProKimi K3 by 3.959.463.3+3.9
- AA-OmniscienceKimi K3 by 3.216.419.7+3.2
- Terminal-bench 3.0Kimi K3 by 2.814.617.4+2.8
- HLE (with tools)Kimi K3 by 2.457.459.8+2.4
- Toolathlon VerifiedKimi K3 by 1.874.776.5+1.8
- Program Benchtie77.377.8tie
Questions people ask
Which is better, Claude Sonnet 5 or Kimi K3?
Kimi K3 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. Claude Sonnet 5 wins none, but costs 33% less.
Which is better for coding?
Kimi K3. It wins 4 of the 5 coding tests both models report; Claude Sonnet 5 wins none, and 1 is a tie.
Which is cheaper?
Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; Kimi K3 costs $3.00 and $15.00. That makes Claude Sonnet 5 about 33% 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.