The Model Index
Up to four models

GLM-5.2 vs Kimi K2.7 Code

On the index (GPT-4 = 100), GLM-5.2 scores 154 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 GLM-5.2
Presets
GLM-5.2
154138–169
WeightsOpen
ReleasedJun 2026
Price in / out$0.0070 / $6.8
Context1.05M
Core tests taken6 of 9
Kimi K2.7 Code
151135–167
WeightsOpen
ReleasedJun 2026
Price in / out$0.70 / $3.75
Context262K
Core tests taken3 of 9

GLM-5.2 and Kimi K2.7 Code are too close to call (3 points apart, within the uncertainty), ahead on 3 of 3 shared core tests, at a similar price.

Test by testthird-party results

GLM-5.2Kimi 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)Surface Evolver BenchSurface Evolver BenchCODINGLiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingCode MigrationCode MigrationLiveCodeBenchLiveCodeBenchProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1DeepSWEDeepSWEWeirdMLWeirdMLAGENTSAPEX-AgentsAPEX-AgentsSkillsBenchSkillsBench
Every result as a table
TestGLM-5.2Kimi K2.7 Code
Reasoning & knowledge
GPQA Diamond (Epoch AI)91.9%87.9%
LiveBench Data Analysis73.7%62.7%
LiveBench IF62.3%56.3%
LiveBench Language76.2%77.9%
LiveBench Reasoning78.6%82.8%
SimpleBench58.8%57.9%
SimpleQA Verified34.2%36.5%
Maths
FrontierMath (tiers 1-3)59.2%54.0%
AIME-style maths (OTIS mock)86.4%95.6%
LiveBench Mathematics89.8%79.6%
Chess puzzles22.0%14.0%
FrontierMath (tier 4)29.3%12.2%
Surface Evolver Bench55.6%48.8%
Coding
LiveBench Agentic Coding51.8%45.7%
LiveBench Coding79.7%74.0%
Code Migration37.9%25.4%
LiveCodeBench69.5%82.0%
ProgramBench0.5%0.0%
SWE-bench82.8%78.2%
Vibe Code Bench v1.164.0%47.2%
DeepSWE43.8%30.5%
WeirdML70.1%54.1%
Agents
APEX-Agents45.2%37.6%
SkillsBench45.1%50.0%

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

This page as a chartDownload PNG