MirrorBench - Level 0 (Guided Mirror Perception): leaderboard
MirrorBench (2026) adapts the mirror self-recognition test to multimodal models: in a simulated scene the model moves a hand to touch a mark on its own body that it can only see in a mirror. Level 0, where the mirror is announced and a chain-of-thought template is given. The score averages task success, step-wise improvement and final and peak completion ratios (at most 1; the final completion ratio is negative when the hand ends farther away than it started); higher is better.
Metric: Average score (mean of task success rate, step-wise improvement ratio, final completion ratio and peak completion ratio, each at most 1; the final completion ratio is negative when the hand ends farther from the mark than it started) at Level 0, where the mirror is announced and a chain-of-thought template is given, over both body settings, on MirrorBench's Isaac Sim mirror self-recognition scenes (7 human and robot bodies, 6 hands, 6 marks; the agent moves its hand with six directional actions to touch a mark on its own body seen in a mirror; step budget the shortest path plus 10), temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 18 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 0.705 | #280 |
| 2 | Claude Sonnet 4.5 | 0.671 | #267 |
| 3 | Gemini 2.5 Flash | 0.618 | #466 |
| 4 | GLM-4.5V | 0.535 | #756 |
| 5 | GPT-4.1 | 0.51 | #506 |
| 6 | GPT-4o | 0.476 | #754 |
| 7 | Qwen 2.5 VL 72B | 0.334 | #782 |
| 8 | Qwen-VL-Max (MirrorBench checkpoint unspecified) | 0.331 | |
| 9 | GPT-4o Mini | 0.086 | #1680 |
| 10 | Qwen 2.5 VL 32B | 0.033 | #944 |
| 11 | InternVL3.5-1B | -0.068 | #6140 |
| 12 | InternVL3.5-4B | -0.243 | #1946 |
| 13 | LLaVA-v1.5-7B | -0.309 | #7642 |
| 14 | InternVL3.5-2B | -0.32 | #3313 |
| 15 | LLaVA-1.6-7B | -0.428 | #4990 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mirrorbench-level-0-guided-mirror-perception · How It Works · Data refreshed daily, snapshot 2026-11-22.