FutureSim - 2026 Q2 (Claude Code): leaderboard
Metric: Final-day Top-1 Accuracy (%). Source: openforecaster.github.io. Saturation forecast: Rough model projection: around 2026. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 (FutureSim Handholding: v1) | 23.81 |
| 2 | Claude Fable 5 (FutureSim Handholding: v1) | 23.19 |
| 3 | GLM 5.2 (FutureSim Handholding: v3) | 14.23 |
| 4 | DeepSeek V4 Flash (0731) (FutureSim Handholding: v3) | 13.05 |
Interactive version: theaggregate.ai/benchmark?slug=futuresim-2026-q2-claude-code · How It Works · Data refreshed daily, snapshot 2026-10-09.