LiveFact: leaderboard
LiveFact (2026) is a monthly fake-news verification benchmark built from fresh news events: models label generated claims Real, Fake or Ambiguous given evidence available three days before, on, or three days after each event. This board is the paper average of twelve scores (accuracy and macro-F1 in two modes at three evidence offsets) on the November 2025 release, in percent; higher is better.
Metric: Average (%) of the twelve LiveFact November 2025 scores (accuracy and macro-F1 in Classification and Inference modes at evidence offsets of -3, 0 and +3 days), 4,392 claims from 737 news events, temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 235B A22B 2507 Instruct | 72.4 | #616 |
| 2 | GPT-OSS-120B | 72.13 | #704 |
| 3 | GPT-5.1 (2025-11-13) | 72.02 | #191 |
| 4 | GPT-5.2 | 71.52 | #185 |
| 5 | Qwen 3 30B A3B 2507 Instruct | 69.46 | #1100 |
| 6 | GPT-4o (2024-08-06) | 67.11 | #743 |
| 7 | GPT-4o Mini (2024-07-18) | 66.12 | #1484 |
| 8 | Qwen 3 32B | 66.03 | #972 |
| 9 | Qwen 3 8B | 63.62 | #1873 |
| 10 | DeepSeek V3.1 | 61.48 | #511 |
| 11 | GPT-OSS-20B | 57.05 | #1183 |
| 12 | Llama 3.3 70B Instruct | 55.85 | #1385 |
| 13 | Qwen 3 4B 2507 Instruct | 55.46 | #2221 |
| 14 | Kimi K2 (Thinking) | 54.6 | |
| 15 | Llama 3.1 8B Instruct | 49.96 | #4600 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=livefact · How It Works · Data refreshed daily, snapshot 2026-11-21.