Claude Sonnet 4 vs Kimi K2.6
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Kimi K2.6 is the stronger all-rounder.
Scores updated · 35 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.
- CodingWriting and fixing software07Kimi K2.67 of 7 tests
- AgentsCarrying out multi-step tasks on its own04Kimi K2.64 of 4 tests
- ReasoningHard problems that need careful thinking03Kimi K2.63 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02Kimi K2.62 of 2 tests
- Long documentsFinding answers in very long texts01Kimi K2.61 of 1 test
- Following instructionsDoing exactly what it is asked01Kimi K2.61 of 1 test
- FactsGetting facts right instead of making them up11Even1 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 73% 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 K2.6 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+74.1points ahead
- Recent programming contest problemsLiveCodeBench v6+41.1points ahead
- Completes tasks by operating a computer desktopOSWorld-Verified+30.9points ahead
Where Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+11.4points ahead
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi K2.6
- LiveCodeBench v6Kimi K2.6 by 41.148.589.6+41.1
- Terminal-Bench 2.1Kimi K2.6 by 29.636.365.9+29.6
- SWE-bench MultilingualKimi K2.6 by 19.856.976.7+19.8
- SWE-bench ProKimi K2.6 by 15.942.758.6+15.9
- Terminal-Bench HardKimi K2.6 by 12.831.143.9+12.8
- SciCodeKimi K2.6 by 11.54051.5+11.5
- SWE-bench VerifiedKimi K2.6 by 7.572.780.2+7.5
AgentsKimi K2.6
- BrowseCompKimi K2.6 by 74.112.286.3+74.1
- OSWorld-VerifiedKimi K2.6 by 30.942.273.1+30.9
- GDPValKimi K2.6 by 17.39.727+17.3
- τ-Bench V3 · BankingKimi K2.6 by 6.616.723.3+6.6
ReasoningKimi K2.6
- Humanity's Last ExamKimi K2.6 by 26.810.737.5+26.8
- GPQA DiamondKimi K2.6 by 13.477.791.1+13.4
- CritPtKimi K2.6 by 7.70.38+7.7
FactsEven
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 11.470.959.5+11.4
- AA-Omniscience · AccuracyKimi K2.6 by 9.922.732.6+9.9
- Vectara HHEM hallucination ratelower is bettertie10.310.8tie
Images and chartsKimi K2.6
- MMMU-ProKimi K2.6 by 17.661.879.4+17.6
- LMArena · VisionKimi K2.6 by 91 rating points11911282+91 rating
Following instructionsKimi K2.6
- IFBenchKimi K2.6 by 21.354.776+21.3
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.
- OJBenchKimi K2.6 by 45.315.360.6+45.3
- HLE (with tools)Kimi K2.6 by 33.720.354+33.7
- τ²-Bench Telecom (AA run)Kimi K2.6 by 31.364.695.9+31.3
- Artificial Analysis Coding IndexKimi K2.6 by 24.237.661.8+24.2
- LiveCodeBenchKimi K2.6 by 21.168.589.6+21.1
- frontiermath_tier_4_v1Kimi K2.6 by 14.6014.6+14.6
- AA IntelligenceKimi K2.6 by 8.118.927+8.1
- AA-OmniscienceKimi K2.6 by 5.10.25.3+5.1
- AA Agentic IndexKimi K2.6 by 4.517.622.1+4.5
- MMLU-ProKimi K2.6 by 3.483.787.1+3.4
- vectara_avg_summary_lengthClaude Sonnet 4 by 29.1 rating points145.8116.7+29.1 rating
- LiveBenchClaude Sonnet 4 by 2.674.872.2+2.6
- vectara_answer_rateKimi K2.6 by 1.198.699.7+1.1
- vectara_factual_consistencytie89.789.2tie
Questions people ask
Which is better, Claude Sonnet 4 or Kimi K2.6?
Kimi K2.6 wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. Claude Sonnet 4 wins none. They are level on facts.
Which is better for coding?
Kimi K2.6. It wins 7 of the 7 coding tests both models report; Claude Sonnet 4 wins none.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; Kimi K2.6 costs $0.95 and $4.00. That makes Kimi K2.6 about 73% cheaper for the same work.
How do you compare the two?
We use the 35 benchmark tests both models have published scores on. The verdict counts the 21 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.