LLMEval-Logic Formalization Fixed — leaderboard
Metric: Accuracy (%). Source: llmeval.com. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 Pro (xHigh) | 60.2 |
| 2 | Kimi K2.5 (Thinking) | 59.4 |
| 3 | Gemini 3.1 Pro (Preview) (Thinking) | 58.1 |
| 4 | Claude Opus 4.6 (Thinking) | 56.9 |
| 5 | Gemini 3.1 Pro (Preview) | 54.5 |
| 6 | Qwen 3.5 Plus (Thinking) | 52.4 |
| 7 | Hy3-preview (Reasoning) | 51.2 |
| 8 | Claude Opus 4.6 (Non-reasoning) | 50 |
| 9 | Kimi K2.5 (Non-reasoning) | 38.6 |
| 10 | Hy3-preview (Non-reasoning) | 24.8 |
Interactive version: theaggregate.ai/benchmark?slug=llmeval-logic-formalization-fixed · How the rankings work · Data refreshed daily, snapshot 2026-07-22.