Claude Opus 4.5 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.
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.
- ReasoningHard problems that need careful thinking05Kimi K35 of 5 tests
- CodingWriting and fixing software04Kimi K34 of 4 tests
- AgentsCarrying out multi-step tasks on its own04Kimi K34 of 4 tests
- MathCompetition and research-level math14Kimi K34 of 5 tests
- FactsGetting facts right instead of making them up03Kimi K33 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02Kimi K32 of 2 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.
Kimi K3 costs 40% less for the same work.
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+54.2points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+37.8points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+34.1points ahead
Where Claude Opus 4.5 pulls ahead
- Fresh competition math problemsLiveBench · Mathematics+6points 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
- LiveBench · Agentic CodingKimi K3 by 22.539.762.2+22.5
- LMArena · WebDevKimi K3 by 186 rating points14691655+186 rating
- SciCodeKimi K3 by 1049.559.5+10
- LiveBench · CodingKimi K3 by 1.879.781.5+1.8
AgentsKimi K3
- BrowseCompKimi K3 by 54.23791.2+54.2
- MCP AtlasKimi K3 by 21.962.384.2+21.9
- OSWorld-VerifiedKimi K3 by 18.566.384.8+18.5
- GDPValKimi K3 by 4.447.351.7+4.4
ReasoningKimi K3
- ARC-AGI-2Kimi K3 by 22.837.660.4+22.8
- CritPtKimi K3 by 18.84.623.4+18.8
- Humanity's Last ExamKimi K3 by 16.830.146.9+16.8
- LiveBench · ReasoningKimi K3 by 10.680.190.7+10.6
- GPQA DiamondKimi K3 by 6.986.693.5+6.9
FactsKimi K3
- AA-Omniscience · Non-hallucinationKimi K3 by 7.83946.8+7.8
- SimpleQA VerifiedKimi K3 by 4.945.750.6+4.9
- AA-Omniscience · AccuracyKimi K3 by 146.647.6+1
Images and chartsKimi K3
- CharXiv (RQ)Kimi K3 by 24.167.291.3+24.1
- MMMU-ProKimi K3 by 6.57480.5+6.5
MathKimi K3
- FrontierMath Tiers 1-3 (v2)Kimi K3 by 37.834.472.2+37.8
- FrontierMath Tier 4Kimi K3 by 34.14.939+34.1
- HMMT Feb. 2026Kimi K3 by 11.785.397+11.7
- LiveBench · MathematicsClaude Opus 4.5 by 690.484.4+6
- AIME 2026Kimi K3 by 1.695.196.7+1.6
Following instructionsKimi K3
- LiveBench · Instruction FollowingKimi K3 by 8.862.571.4+8.8
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.
- ZeroBenchKimi K3 by 38341+38
- ToolathlonKimi K3 by 29.743.573.2+29.7
- CyberGymKimi K3 by 29.450.680+29.4
- Artificial Analysis Coding IndexKimi K3 by 28.447.876.2+28.4
- MATH-VisionKimi K3 by 20.777.197.8+20.7
- DeepSearchQA (F1)Kimi K3 by 18.976.195+18.9
- HLE (with tools)Kimi K3 by 16.643.259.8+16.6
- NL2RepoKimi K3 by 14.843.258+14.8
- AA IntelligenceKimi K3 by 14.529.143.6+14.5
- WorldVQAKimi K3 by 14.236.851+14.2
- ARC-AGI-1Kimi K3 by 12.58294.5+12.5
- AA Agentic IndexClaude Opus 4.5 by 959.650.6+9
- AA-OmniscienceKimi K3 by 5.71419.7+5.7
- livebench_data_analysisKimi K3 by 4.374.478.7+4.3
- livebench_languageKimi K3 by 4.281.385.5+4.2
Questions people ask
Which is better, Claude Opus 4.5 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 Opus 4.5 wins none.
Which is better for coding?
Kimi K3. It wins 4 of the 4 coding tests both models report; Claude Opus 4.5 wins none.
Which is cheaper?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; Kimi K3 costs $3.00 and $15.00. That makes Kimi K3 about 40% 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.