CZ-EVAL - Klokan (Math) — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 Preview (1106) | 58.06 |
| 2 | Claude 3 Opus | 57.81 |
| 3 | Claude 3 Sonnet | 44.28 |
| 4 | Mistral Large | 41.08 |
| 5 | Claude 2.1 | 38.24 |
| 6 | GPT-3.5 Turbo | 32.47 |
| 7 | Claude 3 Haiku | 32.23 |
| 8 | Mistral Medium | 29.4 |
| 9 | Gemini 1.0 Pro | 28.66 |
| 10 | Mixtral 8x7B Instruct | 26.69 |
| 11 | Command R | 24.85 |
| 12 | gemma-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.