Kimi K2.6 vs Claude Opus 5
Wins 1 of 8 areas
Long documents
Wins 6 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math
Claude Opus 5 is the stronger all-rounder.Kimi K2.6 is cheaper and better at long documents.
Scores updated · 39 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.
- CodingWriting and fixing software08Claude Opus 58 of 8 tests
- AgentsCarrying out multi-step tasks on its own06Claude Opus 56 of 6 tests
- ReasoningHard problems that need careful thinking04Claude Opus 54 of 4 tests
- MathCompetition and research-level math03Claude Opus 53 of 3 tests
- FactsGetting facts right instead of making them up12Claude Opus 52 of 3 tests
- Images and chartsUnderstanding pictures, charts and video12Claude Opus 52 of 3 tests
- Long documentsFinding answers in very long texts10Kimi K2.61 of 1 test
- Following instructionsDoing exactly what it is asked00Even0 each · 1 tie
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 K2.6 costs 84% 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 pulls ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+48.5points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+47.6points ahead
- Real work tasks from 44 professionsGDPVal+34.2points ahead
Where Kimi K2.6 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+20.3points ahead
- Reasoning about charts from research papersCharXiv (RQ)+3points ahead
- Reasons across sets of long documentsAA-LCR+1.7points ahead
Every test, side by side
All 39 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 5
- Terminal-Bench 2.1Claude Opus 5 by 23.265.989.1+23.2
- SWE-bench ProClaude Opus 5 by 20.658.679.2+20.6
- LiveBench · Agentic CodingClaude Opus 5 by 18.346.965.2+18.3
- LMArena · WebDevClaude Opus 5 by 183 rating points15091692+183 rating
- SWE-bench VerifiedClaude Opus 5 by 15.880.296+15.8
- SWE-bench MultilingualClaude Opus 5 by 12.876.789.5+12.8
- SciCodeClaude Opus 5 by 4.951.556.4+4.9
- LiveBench · CodingClaude Opus 5 by 2.978.681.5+2.9
AgentsClaude Opus 5
- Terminal-Bench 4.0Claude Opus 5 by 48.50.549+48.5
- GDPValClaude Opus 5 by 34.22761.2+34.2
- τ-Bench V3 · BankingClaude Opus 5 by 18.823.342.1+18.8
- MCP AtlasClaude Opus 5 by 17.768.185.8+17.7
- OSWorld-VerifiedClaude Opus 5 by 10.373.183.4+10.3
- BrowseCompClaude Opus 5 by 4.586.390.8+4.5
ReasoningClaude Opus 5
- CritPtClaude Opus 5 by 21.1829.1+21.1
- Humanity's Last ExamClaude Opus 5 by 17.437.554.9+17.4
- LiveBench · ReasoningClaude Opus 5 by 11.879.491.2+11.8
- GPQA DiamondClaude Opus 5 by 2.191.193.2+2.1
FactsClaude Opus 5
- AA-Omniscience · AccuracyClaude Opus 5 by 28.332.660.9+28.3
- SimpleQA VerifiedClaude Opus 5 by 2534.959.9+25
- AA-Omniscience · Non-hallucinationKimi K2.6 by 20.359.539.2+20.3
Images and chartsClaude Opus 5
- MMMU-ProClaude Opus 5 by 5.379.484.7+5.3
- LMArena · VisionClaude Opus 5 by 39 rating points12821321+39 rating
- CharXiv (RQ)Kimi K2.6 by 386.783.7+3
MathClaude Opus 5
- FrontierMath Tier 4Claude Opus 5 by 47.625.673.2+47.6
- FrontierMath Tiers 1-3 (v2)Claude Opus 5 by 28.457.285.6+28.4
- LiveBench · MathematicsClaude Opus 5 by 11.484.395.7+11.4
Following instructionsEven
- LiveBench · Instruction Followingtie64.463.8tie
Other results10 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.
- GDPval-AA v2Claude Opus 5 by 634 rating points11901824+634 rating
- HiL-Bench (Tools-allowed)Claude Opus 5 by 38.318.757+38.3
- AA Agentic IndexClaude Opus 5 by 34.122.156.2+34.1
- AA-OmniscienceClaude Opus 5 by 31.85.337.1+31.8
- AA IntelligenceClaude Opus 5 by 23.82750.8+23.8
- GDPval-AA (Elo)Claude Opus 5 by 226 rating points14821708+226 rating
- Artificial Analysis Coding IndexClaude Opus 5 by 16.261.878+16.2
- livebench_languageClaude Opus 5 by 13.675.188.7+13.6
- HLE (with tools)Claude Opus 5 by 9.65463.6+9.6
- livebench_data_analysisClaude Opus 5 by 9.565.174.5+9.5
Questions people ask
Which is better, Kimi K2.6 or Claude Opus 5?
Claude Opus 5 wins six of the eight areas we test: coding, agents, reasoning, facts, images and charts and math. Kimi K2.6 wins long documents, and costs 84% less. They are level on following instructions.
Which is better for coding?
Claude Opus 5. It wins 8 of the 8 coding tests both models report; Kimi K2.6 wins none.
Which is cheaper?
Kimi K2.6 costs $0.95 per million input tokens and $4.00 per million output tokens; Claude Opus 5 costs $5.00 and $25.00. That makes Kimi K2.6 about 84% cheaper for the same work.
How do you compare the two?
We use the 39 benchmark tests both models have published scores on. The verdict counts the 29 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.