EgoBench - Dynamic Easy Mode - Micro Accuracy: leaderboard
Metric: MicroAcc (%; share of ground-truth tool calls issued, pooled over tasks, cooperative simulated user revealing one step per turn). Source: arxiv.org. Saturation forecast: Around July 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 44.42 |
| 2 | Qwen 3.5 397B A17B (Non-reasoning) | 41.66 |
| 3 | Seed 2.0 Pro (Non-reasoning) | 38.69 |
| 4 | Qwen 3.6 Plus (Non-reasoning) | 36.58 |
| 5 | Kimi K2.5 (Non-reasoning) | 35.42 |
| 6 | GLM-5V Turbo | 29.7 |
| 7 | MiMo-V2-Omni | 27.99 |
| 8 | Qwen 3 VL 235B A22B Instruct | 15.02 |
Interactive version: theaggregate.ai/benchmark?slug=egobench-dynamic-easy-mode-micro-accuracy · How It Works · Data refreshed daily, snapshot 2026-09-25.