LiveFact (December 2025): 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 accuracy and macro-F1 scores on the December 2025 release of 4,222 claims, in percent; higher is better.
Metric: Average (%) of the twelve LiveFact scores on the December 2025 release (4,222 claims), accuracy and macro-F1 in Classification and Inference modes at evidence offsets of -3, 0 and +3 days; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 235B A22B 2507 Instruct | 71.02 | #625 |
| 2 | Qwen 3 30B A3B 2507 Instruct | 68.32 | #1106 |
| 3 | DeepSeek V3.1 | 66.76 | #511 |
| 4 | Qwen 3 8B | 61.15 | #1890 |
| 5 | Qwen 3 4B 2507 Instruct | 55.81 | #2240 |
| 6 | Llama 3.3 70B Instruct | 54.97 | #1394 |
| 7 | Llama 3.1 8B Instruct | 49.87 | #4655 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=livefact-december-2025 · How It Works · Data refreshed daily, snapshot 2026-11-22.