Kimi K3 vs Claude Sonnet 5.5
Wins 2 of 7 areas
Long documents · Following instructions
Wins 5 of 7 areas
Coding · Agents · Reasoning · Facts · Math
Claude Sonnet 5.5 is the stronger all-rounder.Kimi K3 is better at long documents.
Scores updated · 32 tests both models report · How we compare
Where each one wins
Tests won in each of the seven areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- ReasoningHard problems that need careful thinking04Claude Sonnet 5.54 of 5 tests · 1 tie
- MathCompetition and research-level math03Claude Sonnet 5.53 of 3 tests
- CodingWriting and fixing software13Claude Sonnet 5.53 of 4 tests
- AgentsCarrying out multi-step tasks on its own02Claude Sonnet 5.52 of 2 tests
- FactsGetting facts right instead of making them up12Claude Sonnet 5.52 of 3 tests
- Long documentsFinding answers in very long texts10Kimi K31 of 1 test
- Following instructionsDoing exactly what it is asked10Kimi 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 5.5 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 Claude Sonnet 5.5 pulls ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+51points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+41.5points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+23.5points ahead
Where Kimi K3 pulls ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+14.6points ahead
- Reasons across sets of long documentsAA-LCR+6points ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+5.9points ahead
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 5.5
- LMArena · WebDevClaude Sonnet 5.5 by 117 rating points16571774+117 rating
- LiveBench · CodingClaude Sonnet 5.5 by 9.981.591.4+9.9
- LiveBench · Agentic CodingKimi K3 by 5.962.256.3+5.9
- SciCodeClaude Sonnet 5.5 by 1.559.561+1.5
AgentsClaude Sonnet 5.5
- Terminal-Bench 4.0Claude Sonnet 5.5 by 5112.663.6+51
- GDPValClaude Sonnet 5.5 by 15.251.766.9+15.2
ReasoningClaude Sonnet 5.5
- ARC-AGI-2Claude Sonnet 5.5 by 23.560.483.9+23.5
- SimpleBenchClaude Sonnet 5.5 by 15.260.775.9+15.2
- Humanity's Last ExamClaude Sonnet 5.5 by 8.146.955+8.1
- CritPtClaude Sonnet 5.5 by 823.431.4+8
- LiveBench · Reasoningtie90.791.6tie
FactsClaude Sonnet 5.5
- AA-Omniscience · AccuracyClaude Sonnet 5.5 by 6.447.654+6.4
- AA-Omniscience · Non-hallucinationClaude Sonnet 5.5 by 6.246.853+6.2
- SimpleQA VerifiedKimi K3 by 4.150.646.5+4.1
MathClaude Sonnet 5.5
- FrontierMath Tier 4Claude Sonnet 5.5 by 41.53980.5+41.5
- FrontierMath Tiers 1-3 (v2)Claude Sonnet 5.5 by 16.672.288.8+16.6
- LiveBench · MathematicsClaude Sonnet 5.5 by 11.784.496.1+11.7
Following instructionsKimi K3
- LiveBench · Instruction FollowingKimi K3 by 14.671.456.8+14.6
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.
- Terminal-Bench 4.0Claude Sonnet 5.5 by 5812.670.6+58
- HLE-DiamondClaude Sonnet 5.5 by 26.426.953.3+26.4
- livebench_data_analysisKimi K3 by 19.278.759.5+19.2
- AA-OmniscienceClaude Sonnet 5.5 by 12.619.732.3+12.6
- AA IntelligenceClaude Sonnet 5.5 by 12.443.656+12.4
- livebench_languageKimi K3 by 7.585.578+7.5
- HLE (with tools)Claude Sonnet 5.5 by 4.759.864.5+4.7
- GDP (Surge AI)Claude Sonnet 5.5 by 3.82225.8+3.8
- OfficeQA ProClaude Sonnet 5.5 by 2.363.365.6+2.3
- ARC-AGI-1Claude Sonnet 5.5 by 294.596.5+2
- DeepSWE 1.1Claude Sonnet 5.5 by 26971+2
- Program BenchClaude Sonnet 5.5 by 1.977.879.7+1.9
- Toolathlon VerifiedClaude Sonnet 5.5 by 1.376.577.8+1.3
Questions people ask
Which is better, Kimi K3 or Claude Sonnet 5.5?
Claude Sonnet 5.5 wins five of the seven areas where both have results: coding, agents, reasoning, facts and math. Kimi K3 wins long documents and following instructions.
Which is better for coding?
Claude Sonnet 5.5. It wins 3 of the 4 coding tests both models report; Kimi K3 wins 1.
Which is cheaper?
Kimi K3 costs $3.00 per million input tokens and $15.00 per million output tokens; Claude Sonnet 5.5 costs $2.00 and $10.00. That makes Claude Sonnet 5.5 about 33% cheaper for the same work.
How do you compare the two?
We use the 32 benchmark tests both models have published scores on. The verdict counts the 19 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.