Claude Opus 4.7 vs Kimi K3
Wins 1 of 8 areas
Facts
Wins 7 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math · Long documents · Following instructions
Kimi K3 is the stronger all-rounder.Claude Opus 4.7 is better at facts.
Scores updated · 44 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 own07Kimi K37 of 7 tests
- CodingWriting and fixing software04Kimi K34 of 5 tests · 1 tie
- ReasoningHard problems that need careful thinking24Kimi K34 of 6 tests
- MathCompetition and research-level math13Kimi K33 of 5 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video01Kimi K31 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01Kimi K31 of 1 test
- Following instructionsDoing exactly what it is asked01Kimi K31 of 1 test
- FactsGetting facts right instead of making them up30Claude Opus 4.73 of 3 tests
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 three tests each model wins by the widest margin. Scores are out of 100.
Where Kimi K3 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+11.9points ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+11.5points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+11.4points ahead
Where Claude Opus 4.7 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+15.4points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+10.9points ahead
- Fresh competition math problemsLiveBench · Mathematics+8.5points ahead
Every test, side by side
All 44 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 11.550.762.2+11.5
- LMArena · WebDevKimi K3 by 97 rating points15581655+97 rating
- SciCodeKimi K3 by 554.559.5+5
- Terminal-Bench 2.1Kimi K3 by 1.983.185+1.9
- LiveBench · Codingtie82.181.5tie
AgentsKimi K3
- BrowseCompKimi K3 by 11.979.391.2+11.9
- τ-Bench V3 · BankingKimi K3 by 11.434.646+11.4
- GDPValKimi K3 by 8.942.851.7+8.9
- AA ApexAgentsKimi K3 by 7.433.941.3+7.4
- MCP AtlasKimi K3 by 6.977.384.2+6.9
- OSWorld-VerifiedKimi K3 by 6.87884.8+6.8
- AA IT-Bench SREKimi K3 by 146.747.7+1
ReasoningKimi K3
- ARC-AGI-2Claude Opus 4.7 by 15.475.860.4+15.4
- CritPtKimi K3 by 11.41223.4+11.4
- Humanity's Last ExamKimi K3 by 4.642.346.9+4.6
- LiveBench · ReasoningKimi K3 by 3.587.290.7+3.5
- GPQA DiamondKimi K3 by 2.191.493.5+2.1
- SimpleBenchClaude Opus 4.7 by 161.760.7+1
FactsClaude Opus 4.7
- AA-Omniscience · Non-hallucinationClaude Opus 4.7 by 10.957.746.8+10.9
- AA-Omniscience · AccuracyClaude Opus 4.7 by 1.348.947.6+1.3
- SimpleQA VerifiedClaude Opus 4.7 by 1.151.750.6+1.1
Images and chartsKimi K3
- MMMU-ProKimi K3 by 1.778.880.5+1.7
- CharXiv (RQ)tie9191.3tie
MathKimi K3
- LiveBench · MathematicsClaude Opus 4.7 by 8.592.884.4+8.5
- FrontierMath Tier 4Kimi K3 by 7.331.739+7.3
- HMMT Feb. 2026Kimi K3 by 3.193.997+3.1
- FrontierMath Tiers 1-3 (v2)Kimi K3 by 270.272.2+2
- AIME 2026tie95.896.7tie
Following instructionsKimi K3
- LiveBench · Instruction FollowingKimi K3 by 4.766.771.4+4.7
Other results14 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.
- BabyVisionKimi K3 by 63.522.285.7+63.5
- OfficeQA ProClaude Opus 4.7 by 17.380.663.3+17.3
- WorldVQAKimi K3 by 15.135.951+15.1
- ToolathlonKimi K3 by 13.959.373.2+13.9
- DeepSWEKimi K3 by 13.55467.5+13.5
- AA Agentic IndexKimi K3 by 11.139.550.6+11.1
- AA-OmniscienceClaude Opus 4.7 by 7.627.319.7+7.6
- livebench_languageKimi K3 by 7.677.985.5+7.6
- CyberGymKimi K3 by 6.973.180+6.9
- HLE (with tools)Kimi K3 by 5.154.759.8+5.1
- AA IntelligenceKimi K3 by 2.940.743.6+2.9
- Artificial Analysis Coding IndexKimi K3 by 2.673.676.2+2.6
- ARC-AGI-1Kimi K3 by 2.59294.5+2.5
- livebench_data_analysistie78.378.7tie
Questions people ask
Which is better, Claude Opus 4.7 or Kimi K3?
Kimi K3 wins seven of the eight areas we test: coding, agents, reasoning, images and charts, math, long documents and following instructions. Claude Opus 4.7 wins facts.
Which is better for coding?
Kimi K3. It wins 4 of the 5 coding tests both models report; Claude Opus 4.7 wins none, and 1 is a tie.
Which is cheaper?
Claude Opus 4.7 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 44 benchmark tests both models have published scores on. The verdict counts the 30 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 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.