EgoBench - Dynamic Hard Mode - Micro Accuracy: leaderboard
Metric: MicroAcc (%; share of ground-truth tool calls issued, pooled over tasks, impatient simulated user adding unrelated chatter). Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 42.89 |
| 2 | Seed 2.0 Pro (Non-reasoning) | 37.22 |
| 3 | Qwen 3.5 397B A17B (Non-reasoning) | 36.97 |
| 4 | Qwen 3.6 Plus (Non-reasoning) | 32.95 |
| 5 | Kimi K2.5 (Non-reasoning) | 31.01 |
| 6 | GLM-5V Turbo | 22.41 |
| 7 | MiMo-V2-Omni | 15.35 |
| 8 | Qwen 3 VL 235B A22B Instruct | 4.17 |
Interactive version: theaggregate.ai/benchmark?slug=egobench-dynamic-hard-mode-micro-accuracy · How It Works · Data refreshed daily, snapshot 2026-09-25.