The Model Index
Up to four models

Kimi K2.7 Code vs Inkling

On the index (GPT-4 = 100), Kimi K2.7 Code scores 151 and Inkling 149. 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 Kimi K2.7 Code
Presets
Kimi K2.7 Code
151135–167
WeightsOpen
ReleasedJun 2026
Price in / out$0.70 / $3.75
Context262K
Core tests taken3 of 9
Inkling
149133–165
WeightsOpen
ReleasedJul 2026
Price in / out$1.0 / $4.05
Context524K
Core tests taken6 of 9

Kimi K2.7 Code and Inkling are too close to call (2 points apart, within the uncertainty), ahead on 2 of 3 shared core tests, at a similar price.

Test by testthird-party results

Kimi K2.7 CodeInkling
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)TMLiveBench Data AnalysisLiveBench Data AnalysisTMLiveBench IFLiveBench IFTMLiveBench LanguageLiveBench LanguageTMLiveBench ReasoningLiveBench ReasoningTMSimpleBenchSimpleBenchTMSimpleQA VerifiedSimpleQA VerifiedTMMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)TMAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)TMLiveBench MathematicsLiveBench MathematicsTMChess puzzlesChess puzzlesTMFrontierMath (tier 4)FrontierMath (tier 4)TMCODINGLiveBench Agentic CodingLiveBench Agentic CodingTMLiveBench CodingLiveBench CodingTMCode MigrationCode MigrationTMLiveCodeBenchLiveCodeBenchTMProgramBenchProgramBenchTMSWE-benchSWE-benchTMVibe Code Bench v1.1Vibe Code Bench v1.1TMWeirdMLWeirdMLTMAGENTSAPEX-AgentsAPEX-AgentsTMSkillsBenchSkillsBenchTM
Every result as a table
TestKimi K2.7 CodeInkling
Reasoning & knowledge
GPQA Diamond (Epoch AI)87.9%88.3%
LiveBench Data Analysis62.7%72.8%
LiveBench IF56.3%70.1%
LiveBench Language77.9%73.5%
LiveBench Reasoning82.8%78.3%
SimpleBench57.9%50.0%
SimpleQA Verified36.5%40.3%
Maths
FrontierMath (tiers 1-3)54.0%33.3%
AIME-style maths (OTIS mock)95.6%88.9%
LiveBench Mathematics79.6%88.4%
Chess puzzles14.0%21.0%
FrontierMath (tier 4)12.2%4.9%
Coding
LiveBench Agentic Coding45.7%49.4%
LiveBench Coding74.0%71.0%
Code Migration25.4%11.8%
LiveCodeBench82.0%85.5%
ProgramBench0.0%0.0%
SWE-bench78.2%77.6%
Vibe Code Bench v1.147.2%19.2%
WeirdML54.1%32.3%
Agents
APEX-Agents37.6%33.8%
SkillsBench50.0%26.1%

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

This page as a chartDownload PNG