Claude Opus 5.5 vs Kimi K3
Wins 6 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math
Wins 2 of 8 areas
Long documents · Following instructions
Claude Opus 5.5 is the stronger all-rounder.Kimi K3 is cheaper and better at long documents.
Both rank among the ten best models we track in agents.
Scores updated · 38 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 thinking50Claude Opus 5.55 of 5 tests
- CodingWriting and fixing software40Claude Opus 5.54 of 4 tests
- MathCompetition and research-level math30Claude Opus 5.53 of 3 tests
- AgentsCarrying out multi-step tasks on its own21Claude Opus 5.52 of 4 tests · 1 tie
- FactsGetting facts right instead of making them up21Claude Opus 5.52 of 3 tests
- Images and chartsUnderstanding pictures, charts and video10Claude Opus 5.51 of 1 test
- Long documentsFinding answers in very long texts01Kimi K31 of 1 test
- Following instructionsDoing exactly what it is asked01Kimi K31 of 1 test
Images and charts, 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 25% 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 Opus 5.5 pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+56points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+47points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+31.3points ahead
Where Kimi K3 pulls ahead
- Finds the root cause of IT system incidentsAA IT-Bench SRE+9.5points ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+5.7points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+5.4points ahead
Every test, side by side
All 38 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 5.5
- LMArena · WebDevClaude Opus 5.5 by 157 rating points18151658+157 rating
- LiveBench · Agentic CodingClaude Opus 5.5 by 9.571.762.2+9.5
- LiveBench · CodingClaude Opus 5.5 by 7.889.381.5+7.8
- SciCodeClaude Opus 5.5 by 7.466.959.5+7.4
AgentsClaude Opus 5.5
- Terminal-Bench 4.0Claude Opus 5.5 by 4759.612.6+47
- GDPValClaude Opus 5.5 by 16.668.351.7+16.6
- AA IT-Bench SREKimi K3 by 9.538.247.7+9.5
- BrowseComptie90.891.2tie
ReasoningClaude Opus 5.5
- ARC-AGI-2Claude Opus 5.5 by 31.391.760.4+31.3
- SimpleBenchClaude Opus 5.5 by 27.788.460.7+27.7
- Humanity's Last ExamClaude Opus 5.5 by 14.561.446.9+14.5
- CritPtClaude Opus 5.5 by 8.331.723.4+8.3
- LiveBench · ReasoningClaude Opus 5.5 by 1.592.290.7+1.5
FactsClaude Opus 5.5
- SimpleQA VerifiedClaude Opus 5.5 by 21.672.250.6+21.6
- AA-Omniscience · AccuracyClaude Opus 5.5 by 18.666.247.6+18.6
- AA-Omniscience · Non-hallucinationKimi K3 by 5.441.446.8+5.4
Images and chartsClaude Opus 5.5
- MMMU-ProClaude Opus 5.5 by 7.287.780.5+7.2
MathClaude Opus 5.5
- FrontierMath Tier 4Claude Opus 5.5 by 569539+56
- FrontierMath Tiers 1-3 (v2)Claude Opus 5.5 by 1991.272.2+19
- LiveBench · MathematicsClaude Opus 5.5 by 12.797.184.4+12.7
Following instructionsKimi K3
- LiveBench · Instruction FollowingKimi K3 by 5.765.771.4+5.7
Other results16 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 Opus 5.5 by 53.866.412.6+53.8
- HLE-DiamondClaude Opus 5.5 by 4167.926.9+41
- AA-OmniscienceClaude Opus 5.5 by 26.746.419.7+26.7
- OSWorld 2.0Claude Opus 5.5 by 23.581.858.3+23.5
- HiL-Bench (Tools-allowed)Claude Opus 5.5 by 16.35942.7+16.3
- AA IntelligenceClaude Opus 5.5 by 1457.643.6+14
- Program BenchClaude Opus 5.5 by 13.491.277.8+13.4
- PostTrainBenchClaude Opus 5.5 by 12.749.336.6+12.7
- HLE (with tools)Claude Opus 5.5 by 7.967.759.8+7.9
- DeepSWE 1.1Claude Opus 5.5 by 5.274.269+5.2
- OfficeQA ProClaude Opus 5.5 by 4.467.763.3+4.4
- GDP (Surge AI)Claude Opus 5.5 by 4.226.222+4.2
- ARC-AGI-1Claude Opus 5.5 by 397.594.5+3
- livebench_data_analysisClaude Opus 5.5 by 1.680.378.7+1.6
- Toolathlon VerifiedClaude Opus 5.5 by 1.377.876.5+1.3
- livebench_languagetie86.385.5tie
Questions people ask
Which is better, Claude Opus 5.5 or Kimi K3?
Claude Opus 5.5 wins six of the eight areas we test: coding, agents, reasoning, facts, images and charts and math. Kimi K3 wins long documents and following instructions, and costs 25% less.
Which is better for coding?
Claude Opus 5.5. It wins 4 of the 4 coding tests both models report; Kimi K3 wins none.
Which is cheaper?
Claude Opus 5.5 costs $4.00 per million input tokens and $20.00 per million output tokens; Kimi K3 costs $3.00 and $15.00. That makes Kimi K3 about 25% cheaper for the same work.
How do you compare the two?
We use the 38 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 16 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.