The Model Index
Up to four models

Claude Opus 4.5 vs Kimi K2.7 Code

On the index (GPT-4 = 100), Claude Opus 4.5 scores 152 and Kimi K2.7 Code 151. 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 Opus 4.5
Presets
Claude Opus 4.5
152136–168
WeightsClosed
ReleasedNov 2025
Price in / out$5.0 / $25
Context200K
Core tests taken5 of 9
Kimi K2.7 Code
151135–167
WeightsOpen
ReleasedJun 2026
Price in / out$0.70 / $3.75
Context262K
Core tests taken3 of 9

Claude Opus 4.5 and Kimi K2.7 Code are too close to call (1 point apart, within the uncertainty), ahead on 0 of 2 shared core tests, at 6.8× the price.

Test by testthird-party results

Claude Opus 4.5Kimi K2.7 Code
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)LiveBench Data AnalysisLiveBench Data AnalysisLiveBench IFLiveBench IFLiveBench LanguageLiveBench LanguageLiveBench ReasoningLiveBench ReasoningSimpleBenchSimpleBenchSimpleQA VerifiedSimpleQA VerifiedMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)LiveBench MathematicsLiveBench MathematicsChess puzzlesChess puzzlesFrontierMath (tier 4)FrontierMath (tier 4)CODINGLiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1WeirdMLWeirdML
Every result as a table
TestClaude Opus 4.5Kimi K2.7 Code
Reasoning & knowledge
GPQA Diamond (Epoch AI)86.1%87.9%
LiveBench Data Analysis74.4%62.7%
LiveBench IF62.5%56.3%
LiveBench Language81.3%77.9%
LiveBench Reasoning80.1%82.8%
SimpleBench62.0%57.9%
SimpleQA Verified45.7%36.5%
Maths
FrontierMath (tiers 1-3)34.4%54.0%
AIME-style maths (OTIS mock)86.1%95.6%
LiveBench Mathematics90.4%79.6%
Chess puzzles14.0%14.0%
FrontierMath (tier 4)4.9%12.2%
Coding
LiveBench Agentic Coding39.7%45.7%
LiveBench Coding79.7%74.0%
LiveCodeBench83.7%82.0%
SWE-bench76.4%78.2%
Vibe Code Bench v1.120.6%47.2%
WeirdML63.7%54.1%
Task length · METR45 sec

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

This page as a chartDownload PNG