The Model Index
Up to four models

Gemini 3 Pro vs Kimi K2 Thinking

On the index (GPT-4 = 100), Gemini 3 Pro scores 160 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 Gemini 3 Pro
Presets
Gemini 3 Pro
160145–176
WeightsClosed
ReleasedNov 2025
Price in / out–
Context–
Core tests taken5 of 9
Kimi K2 Thinking
139123–156
WeightsOpen
ReleasedNov 2025
Price in / out$0.60 / $2.5
Context262K
Core tests taken2 of 9

Gemini 3 Pro leads Kimi K2 Thinking by 21 points, ahead on 2 of 2 shared core tests.

Test by testthird-party results

Gemini 3 ProKimi K2 Thinking
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)CL-benchCL-benchSimpleBenchSimpleBenchMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)FrontierMath (2025 set)FrontierMath (2025 set)FrontierMath tier 4 (2025 set)FrontierMath tier 4 (2025 set)CODINGTerminal-Bench 2.0 (Terminus 2 runs)Terminal-Bench 2.0 (Terminus 2 runs)WeirdMLWeirdML
Every result as a table
TestGemini 3 ProKimi K2 Thinking
Reasoning & knowledge
GPQA Diamond (Epoch AI)92.6%84.2%
CL-bench15.8%17.6%
SimpleBench76.4%39.6%
Maths
AIME-style maths (OTIS mock)91.4%83.1%
FrontierMath (2025 set)37.6%21.4%
FrontierMath tier 4 (2025 set)18.8%0.0%
Coding
Terminal-Bench 2.0 (Terminus 2 runs)56.9%35.7%
WeirdML69.9%42.8%
Task length · METR43 sec36 sec

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

This page as a chartDownload PNG