The Model Index
Up to four models

Kimi K2 Thinking vs Qwen3.6-35B-A3B

On the index (GPT-4 = 100), Kimi K2 Thinking scores 139 and Qwen3.6-35B-A3B 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 Kimi K2 Thinking
Presets
Kimi K2 Thinking
139123–156
WeightsOpen
ReleasedNov 2025
Price in / out$0.60 / $2.5
Context262K
Core tests taken2 of 9
Qwen3.6-35B-A3B
139122–155
WeightsOpen
ReleasedApr 2026
Price in / out$0.10 / $0.90
Context262K
Core tests taken2 of 9

Kimi K2 Thinking and Qwen3.6-35B-A3B are too close to call (1 point apart, within the uncertainty), ahead on 0 of 1 shared core tests, at 3.6× the price.

Test by testthird-party results

Kimi K2 ThinkingQwen3.6-35B-A3B
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)CODINGWeirdMLWeirdML
Every result as a table
TestKimi K2 ThinkingQwen3.6-35B-A3B
Reasoning & knowledge
GPQA Diamond (Epoch AI)84.2%84.9%
Maths
AIME-style maths (OTIS mock)83.1%86.7%
Coding
WeirdML42.8%34.5%
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