ForecastBench-Sim Pandemic - Unconditional: leaderboard
Metric: Brier Score (0-1; scored responses). Source: raw.githubusercontent.com. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 | 0.05 |
| 2 | Qwen 2.5 72B Instruct | 0.05 |
| 3 | Claude Haiku 4.5 (20251001) | 0.05 |
| 4 | Llama 3.1 70B Instruct | 0.05 |
| 5 | DeepSeek V3 | 0.05 |
| 6 | GPT-5 | 0.05 |
| 7 | GPT-5.1 | 0.06 |
| 8 | O3 Mini (2025-01-31) | 0.06 |
| 9 | O4 Mini (2025-04-16) | 0.07 |
| 10 | Gemini 2.5 Pro | 0.09 |
| 11 | GPT-5 Mini | 0.09 |
| 12 | GPT-5 Nano | 0.1 |
| 13 | O3 (2025-04-16) | 0.1 |
| 14 | Claude Sonnet 4.5 | 0.12 |
| 15 | Grok 4 | 0.19 |
Interactive version: theaggregate.ai/benchmark?slug=forecastbench-sim-pandemic-unconditional · How It Works · Data refreshed daily, snapshot 2026-09-19.