EMem-Bench - Interaction Failure: leaderboard
Metric: Success rate (%; the 263 Interaction Failure episodes, avoiding a target that an earlier failed action showed to be unusable; full-context condition: the complete interaction history as sanitized text plus the current 500 x 500 RGB view, one primitive action per call with deterministic decoding and at most eight target-task steps in AI2-THOR and ProcTHOR homes; an episode succeeds only if the simulator reaches the target terminal state). Source: arxiv.org. Saturation forecast: Around December 2026. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 60.5 |
| 2 | Gemini 2.5 Pro | 55.1 |
| 3 | Qwen 3.6 27B | 54.4 |
| 4 | GPT-5.4 | 51 |
| 5 | Qwen 3 VL 32B Instruct | 45.3 |
| 6 | InternVL3-38B | 29.3 |
| 7 | Qwen 3 VL 4B Instruct | 20.9 |
| 8 | GPT-5.4 Mini | 19 |
| 9 | Qwen 3 VL 8B Instruct | 11.8 |
| 10 | InternVL3-8B | 5.3 |
Interactive version: theaggregate.ai/benchmark?slug=emem-bench-interaction-failure · How It Works · Data refreshed daily, snapshot 2026-09-26.