HalluWorld - Terminal: leaderboard
Hallucination rate on HalluWorld-Terminal (2026): probes about recorded Terminal-Bench agent trajectories, with golden answers grounded in file-system diffs, covering perceptual, memory, causal, uncertainty and compound questions. Percent; lower is better.
Metric: Hallucination rate (%) over the 529 HalluWorld-Terminal probes about recorded Terminal-Bench agent trajectories (golden answers grounded in file-system diffs, context up to 60k characters), 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: Around February 2027. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5.5 | Medium | 5.9 | #56 |
| 2 | O3 | 10.2 | #242 | |
| 3 | O4 Mini | 14.2 | #372 | |
| 4 | Claude Opus 4.6 | Medium | 15.7 | #114 |
| 5 | Claude Sonnet 4.6 | Medium | 17.8 | #179 |
| 6 | O3 Mini | 21 | #552 | |
| 7 | GLM-5 | Non-reasoning | 26.3 | #276 |
| 8 | GPT-4o | 38.4 | #754 | |
| 9 | DeepSeek V3.1 | Non-reasoning | 45.6 | #511 |
| 10 | GPT-5.4 Mini | Non-reasoning | 50.3 | #409 |
| 11 | Qwen 3 30B A3B | Non-reasoning | 51 | #1165 |
| 12 | GPT-4o Mini | 51.8 | #1680 | |
| 13 | Kimi K2.6 | Non-reasoning | 56.5 | #197 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=halluworld-terminal · How It Works · Data refreshed daily, snapshot 2026-11-22.