The Model Index
Up to four models

Kimi K2 (Sep 2025) vs Mistral Medium 3.5

On the index (GPT-4 = 100), Kimi K2 (Sep 2025) scores 132 and Mistral Medium 3.5 131. 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 (Sep 2025)
Presets
Kimi K2 (Sep 2025)
132116–148
WeightsOpen
ReleasedSep 2025
Price in / out$0.60 / $2.5
Context262K
Core tests taken0 of 9
Mistral Medium 3.5
131114–148
WeightsOpen
ReleasedApr 2026
Price in / out$1.5 / $7.5
Context262K
Core tests taken1 of 9

Kimi K2 (Sep 2025) and Mistral Medium 3.5 are too close to call (1 point apart, within the uncertainty), and costs 2.8× less.

Test by testthird-party results

Kimi K2 (Sep 2025)Mistral Medium 3.5
0%25%50%75%100%CODINGWeirdMLWeirdML
Every result as a table
TestKimi K2 (Sep 2025)Mistral Medium 3.5
Coding
WeirdML36.7%43.7%

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

This page as a chartDownload PNG