CZ-EVAL - Klokan (Math) — leaderboard

Metric: Accuracy (%). Source: huggingface.co. 12 models tracked.

Top models

#ModelScore
1GPT-4 Preview (1106)58.06
2Claude 3 Opus57.81
3Claude 3 Sonnet44.28
4Mistral Large41.08
5Claude 2.138.24
6GPT-3.5 Turbo32.47
7Claude 3 Haiku32.23
8Mistral Medium29.4
9Gemini 1.0 Pro28.66
10Mixtral 8x7B Instruct26.69
11Command R24.85
12gemma-7B (IT)16.97

Interactive version: aibenchmarks.dev/benchmark?slug=cz-eval-klokan-math · How the rankings work · Data refreshed daily, snapshot 2026-07-08.