CESBench - Judgment: leaderboard
Metric: Judgment score (%; the 67 true-or-false security claims: a wrong verdict scores 0, a right one earns the mean of four justification rubric points judged 0, 0.5 or 1; 380 expert-written items on cryptographic engineering security for IoT devices; zero-shot, temperature 0, no tools, provider default reasoning mode; judgment and scenario answers scored by a Qwen3.5-397B judge from outside the evaluated set). Source: arxiv.org. Saturation forecast: Around 2029. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5.2 | 58.8 |
| 2 | Kimi K2.6 | 58 |
| 3 | Gemini 3.7 Flash | 54.9 |
| 4 | GPT-5.6 Luna | 54.5 |
| 5 | MiniMax-M2.5 | 48.3 |
| 6 | DeepSeek V4 Pro | 47 |
| 7 | Hunyuan A13B-Instruct | 43.3 |
| 8 | DeepSeek V3 | 41.2 |
| 9 | Ling-flash-2.0 | 40.1 |
| 10 | GLM-4 32B (0414) | 38.6 |
| 11 | Llama 4 Maverick | 34.9 |
Interactive version: theaggregate.ai/benchmark?slug=cesbench-judgment · How It Works · Data refreshed daily, snapshot 2026-09-26.