FLY-EVAL++ - History-Conditioned Prediction - Total: leaderboard
Metric: M1 total score (%). Source: arxiv.org. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 97.31 |
| 2 | Gemini 3 Pro | 97.23 |
| 3 | DeepSeek V3 | 97.14 |
| 4 | DeepSeek V3.2 Exp | 97.08 |
| 5 | Qwen 2.5 32B | 97.02 |
| 6 | Qwen 3 235B A22B | 97.01 |
| 7 | Qwen 3 32B | 96.98 |
| 8 | Claude 3.7 Sonnet (20250219) | 96.96 |
| 9 | Qwen3-Next-80B | 96.94 |
| 10 | GPT-4o | 96.92 |
| 11 | Llama 3.1 405B | 96.85 |
| 12 | Claude Sonnet 4.5 | 96.84 |
| 13 | O4 Mini | 96.79 |
| 14 | Kimi K2 (Thinking) | 96.77 |
| 15 | Gemini 2.5 Pro | 96.76 |
Interactive version: theaggregate.ai/benchmark?slug=fly-eval-plus-plus-history-conditioned-prediction-total · How It Works · Data refreshed daily, snapshot 2026-09-19.