The Model Index
Up to four models

DeepSeek-V3.2-Exp vs Kimi K2 Thinking

On the index (GPT-4 = 100), DeepSeek-V3.2-Exp scores 140 and Kimi K2 Thinking 139. 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 DeepSeek-V3.2-Exp
Presets
DeepSeek-V3.2-Exp
140124–157
WeightsOpen
ReleasedSep 2025
Price in / out$0.27 / $0.41
Context164K
Core tests taken0 of 9
Kimi K2 Thinking
139123–156
WeightsOpen
ReleasedNov 2025
Price in / out$0.60 / $2.5
Context262K
Core tests taken2 of 9

DeepSeek-V3.2-Exp and Kimi K2 Thinking are too close to call (1 point apart, within the uncertainty), and costs 3.5× less.

Test by testthird-party results

DeepSeek-V3.2-ExpKimi K2 Thinking
0%25%50%75%100%REASONING & KNOWLEDGECL-benchCL-benchCODINGWeirdMLWeirdML
Every result as a table
TestDeepSeek-V3.2-ExpKimi K2 Thinking
Reasoning & knowledge
CL-bench13.2%17.6%
Coding
WeirdML39.5%42.8%
Task length · METR36 sec

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

This page as a chartDownload PNG