The Model Index
Up to four models

Inkling-Small vs Kimi K2.7 Code

On the index (GPT-4 = 100), Inkling-Small scores 153 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 Inkling-Small
Presets
Inkling-Small
153137–169
WeightsOpen
ReleasedJul 2026
Price in / out$0.45 / $1.2
Context524K
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

Inkling-Small and Kimi K2.7 Code are too close to call (3 points apart, within the uncertainty), ahead on 1 of 2 shared core tests, and costs 2.3× less.

Test by testthird-party results

Inkling-SmallKimi K2.7 Code
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)TMSimpleQA VerifiedSimpleQA VerifiedTMMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)TMAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)TMFrontierMath (tier 4)FrontierMath (tier 4)TMCODINGCode MigrationCode MigrationTMLiveCodeBenchLiveCodeBenchTMProgramBenchProgramBenchTMSWE-benchSWE-benchTMVibe Code Bench v1.1Vibe Code Bench v1.1TMAGENTSSkillsBenchSkillsBenchTM
Every result as a table
TestInkling-SmallKimi K2.7 Code
Reasoning & knowledge
GPQA Diamond (Epoch AI)88.5%87.9%
SimpleQA Verified19.1%36.5%
Maths
FrontierMath (tiers 1-3)46.3%54.0%
AIME-style maths (OTIS mock)90.0%95.6%
FrontierMath (tier 4)17.1%12.2%
Coding
Code Migration13.7%25.4%
LiveCodeBench85.9%82.0%
ProgramBench0.5%0.0%
SWE-bench82.2%78.2%
Vibe Code Bench v1.119.1%47.2%
Agents
SkillsBench33.6%50.0%

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

This page as a chartDownload PNG