HalluWorld - Grid Uncertainty: leaderboard
Uncertainty hallucination in HalluWorld-Grid (2026), MiniGrid worlds whose ground truth comes from the environment state: the rate of hallucinated answers to questions where the evidence is insufficient and the model should abstain. Percent; lower is better.
Metric: Hallucination rate (%) on the uncertainty probes (abstaining when the evidence is insufficient, 5 levels) of HalluWorld-Grid (MiniGrid worlds whose ground truth comes from the environment state), micro-averaged over levels and serializers, temperature 0 where supported, thinking models at medium effort with up to 16k thinking tokens, every model at most 256 answer tokens; lower is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GLM-5 | Non-reasoning | 0 | #269 |
| 2 | GPT-5.5 | Medium | 0.1 | #54 |
| 3 | O3 | 0.3 | #237 | |
| 4 | GPT-4o | 0.5 | #751 | |
| 5 | O4 Mini | 0.9 | #368 | |
| 6 | Claude Sonnet 4.6 | 1.1 | #173 | |
| 7 | Kimi K2.6 | Non-reasoning | 1.9 | #192 |
| 8 | Claude Opus 4.6 | 3.4 | #113 | |
| 9 | DeepSeek V3 (0324) | 4.6 | #715 | |
| 10 | GPT-4o Mini | 5.1 | #1667 | |
| 11 | GPT-5.4 Mini | Non-reasoning | 5.7 | #406 |
| 12 | O3 Mini | 5.9 | #546 | |
| 13 | Qwen 3 30B A3B | Non-reasoning | 13.2 | #1156 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=halluworld-grid-uncertainty · How It Works · Data refreshed daily, snapshot 2026-11-21.