LLMEval-Logic Formalization Free — leaderboard
Metric: Accuracy (%). Source: llmeval.com. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) (Thinking) | 45.1 |
| 2 | Gemini 3.1 Pro (Preview) | 44.3 |
| 3 | Claude Opus 4.6 (Non-reasoning) | 43.5 |
| 4 | Claude Opus 4.6 (Thinking) | 38.6 |
| 5 | Kimi K2.5 (Thinking) | 36.2 |
| 6 | Qwen 3.5 Plus (Thinking) | 36.2 |
| 7 | GPT-5.4 Pro (xHigh) | 32.9 |
| 8 | Hy3-preview (Reasoning) | 27.6 |
| 9 | Kimi K2.5 (Non-reasoning) | 27.2 |
| 10 | Hy3-preview (Non-reasoning) | 21.9 |
Interactive version: theaggregate.ai/benchmark?slug=llmeval-logic-formalization-free · How the rankings work · Data refreshed daily, snapshot 2026-07-22.