The Model Index
Up to four models

Claude Sonnet 4.6 vs Kimi K2.5

On the index (GPT-4 = 100), Claude Sonnet 4.6 scores 159 and Kimi K2.5 145. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Claude Sonnet 4.6
Presets
Claude Sonnet 4.6
159143–175
WeightsClosed
ReleasedFeb 2026
Price in / out$3.0 / $15
Context1M
Core tests taken5 of 9
Kimi K2.5
145130–161
WeightsOpen
ReleasedJan 2026
Price in / out$0.50 / $2.5
Context262K
Core tests taken5 of 9

Claude Sonnet 4.6 leads Kimi K2.5 by 13 points, ahead on 3 of 4 shared core tests, at 6.0× the price.

Test by testthird-party results

Claude Sonnet 4.6Kimi K2.5
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProSimpleQA VerifiedSimpleQA VerifiedMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)FrontierMath (2025 set)FrontierMath (2025 set)FrontierMath tier 4 (2025 set)FrontierMath tier 4 (2025 set)CODINGSWE-bench VerifiedSWE-bench VerifiedCode MigrationCode MigrationLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1WeirdMLWeirdMLPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)CorpFin v2CorpFin v2EMBEMBLegal Research BenchLegal Research BenchMortgageTaxMortgageTaxTaxEval v2TaxEval v2NOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1
Every result as a table
TestClaude Sonnet 4.6Kimi K2.5
Reasoning & knowledge
GPQA Diamond (Epoch AI)87.4%87.6%
GPQA Diamond (Vals AI)85.6%84.1%
MMLU Pro87.3%85.9%
MMMU Pro83.6%84.3%
SimpleQA Verified35.5%34.3%
Maths
AIME-style maths (OTIS mock)85.8%92.2%
FrontierMath (2025 set)32.4%27.9%
FrontierMath tier 4 (2025 set)8.3%4.2%
Coding
SWE-bench Verified75.2%73.8%
Code Migration39.9%7.0%
LiveCodeBench82.1%83.9%
SWE-bench77.4%70.0%
Vibe Code Bench v1.151.5%17.5%
WeirdML66.1%45.6%
Professional work
Finance Agent (v2)51.0%35.8%
CorpFin v265.3%68.3%
EMB60.2%28.5%
Legal Research Bench38.5%15.9%
MortgageTax67.7%66.5%
TaxEval v277.1%74.2%
Novel problems
ARC-AGI-260.4%11.8%
ARC-AGI-186.5%65.3%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG