RPCBench - Domain - MIND-small - Fact Fabrication: leaderboard

Metric: Fact Fabrication Rate (%). Source: github.com. Saturation forecast: Estimated already saturated. 11 models tracked.

Top models

#ModelScore
1Qwen 3.5 122B A10B0.71
2Qwen 3.5 35B A3B1.28
3Qwen 3.5 397B A17B1.56
4Qwen 3.5 Plus2.13
5GPT-5.54.13
6DeepSeek V4 Pro6.12
7DeepSeek V4 Flash8.68
8Gemini 3.1 Pro (Preview)8.82
9Claude Sonnet 4.612.8
10Llama 3.1 70B Instruct45.38
11Llama 3.1 8B Instruct52.92

Interactive version: theaggregate.ai/benchmark?slug=rpcbench-domain-mind-small-fact-fabrication · How It Works · Data refreshed daily, snapshot 2026-09-24.