Grip on LLMs - HonestCityBench - Outdated Information: leaderboard

Metric: Appropriate acknowledgement rate (%; LLM judge). Source: arxiv.org. 31 models tracked.

Top models

#ModelScore
1Mistral Small 366
2Llama 3.1 8B Instruct62
3GPT-4o61
4Phi-4 Mini Instruct52
5GPT-4o Mini42
6GEITje-7B-ultra32
7DeepSeek R1 Distill Qwen 32B27
8GPT-5 Mini15
9Qwen 3 32B14
10aya-expanse-32B14
11command-r7B-12-202414
12GPT-5 Nano12
13Qwen 3 8B12
14GPT-510
15SmolLM3-3B10

Interactive version: theaggregate.ai/benchmark?slug=grip-on-llms-honestcitybench-outdated-information · How It Works · Data refreshed daily, snapshot 2026-09-19.