Claude Sonnet 4.5 vs Kimi K3
Wins 0 of 7 areas
—
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents
Kimi K3 is the stronger all-rounder.
Scores updated · 30 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.
- AgentsCarrying out multi-step tasks on its own06Kimi K36 of 6 tests
- ReasoningHard problems that need careful thinking05Kimi K35 of 5 tests
- CodingWriting and fixing software03Kimi K33 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02Kimi K32 of 2 tests
- MathCompetition and research-level math02Kimi 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
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.
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
- Finds hard-to-locate facts by browsing the webBrowseComp+67.1points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+48.3points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+46.8points ahead
Where Claude Sonnet 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+4.1points ahead
Every test, side by side
All 30 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi K3
- Terminal-Bench 2.1Kimi K3 by 29.255.885+29.2
- LMArena · WebDevKimi K3 by 265 rating points13931658+265 rating
- SciCodeKimi K3 by 13.845.759.5+13.8
AgentsKimi K3
- BrowseCompKimi K3 by 67.124.191.2+67.1
- MCP AtlasKimi K3 by 40.443.884.2+40.4
- GDPValKimi K3 by 31.320.551.8+31.3
- OSWorld-VerifiedKimi K3 by 23.461.484.8+23.4
- τ-Bench V3 · BankingKimi K3 by 21.524.546+21.5
- Terminal-Bench 4.0Kimi K3 by 12.6012.6+12.6
ReasoningKimi K3
- ARC-AGI-2Kimi K3 by 46.813.660.4+46.8
- Humanity's Last ExamKimi K3 by 29.117.846.9+29.1
- CritPtKimi K3 by 22.31.123.4+22.3
- GPQA DiamondKimi K3 by 10.183.493.5+10.1
- SimpleBenchKimi K3 by 6.454.360.7+6.4
FactsKimi K3
- SimpleQA VerifiedKimi K3 by 19.930.750.6+19.9
- AA-Omniscience · AccuracyKimi K3 by 14.732.947.6+14.7
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 4.150.946.8+4.1
Images and chartsKimi K3
- CharXiv (RQ)Kimi K3 by 24.167.291.3+24.1
- MMMU-ProKimi K3 by 11.868.780.5+11.8
MathKimi K3
- FrontierMath Tiers 1-3 (v2)Kimi K3 by 48.323.972.2+48.3
- FrontierMath Tier 4Kimi K3 by 36.62.439+36.6
Other results8 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.
- AA Agentic IndexKimi K3 by 33.117.550.6+33.1
- ToolathlonKimi K3 by 32.24173.2+32.2
- ARC-AGI-1Kimi K3 by 30.863.794.5+30.8
- HLE (with tools)Kimi K3 by 27.83259.8+27.8
- Artificial Analysis Coding IndexKimi K3 by 24.152.176.2+24.1
- AA IntelligenceKimi K3 by 22.920.743.6+22.9
- AA-OmniscienceKimi K3 by 19.8-0.119.7+19.8
- matharena_visual_math_overallKimi K3 by 15.575.891.3+15.5
Questions people ask
Which is better, Claude Sonnet 4.5 or Kimi K3?
Kimi K3 wins all seven areas where both have results: coding, agents, reasoning, facts, images and charts, math and long documents. Claude Sonnet 4.5 wins none.
Which is better for coding?
Kimi K3. It wins 3 of the 3 coding tests both models report; Claude Sonnet 4.5 wins none.
Which is cheaper?
Claude Sonnet 4.5 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 30 benchmark tests both models have published scores on. The verdict counts the 22 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.