HINTBench - Coarse Risk-Step Localization: leaderboard
HINTBench (2026) asks an LLM to audit long-horizon agent trajectories for intrinsic, non-attack risks such as acting beyond what the user authorized or skipping confirmations before irreversible actions. This board scores locating the risky steps (within three steps) under five constraint categories, ignoring the type, as F1 in percent, higher is better.
Metric: Localization F1 (%) for coarse risk-step localization (five constraint categories; a predicted risky step matches a gold step within plus or minus 3 steps; type ignored) over the 536 synthetic HINTBench agent trajectories (400 risky, 136 safe, 24 steps on average, unanimously accepted by three human verifiers) audited zero-shot by a general LLM for intrinsic, non-attack risk under a five-constraint taxonomy (goal, capability, factual, procedural, state constraints), each model at its stated reasoning setting; higher is better. Source: arxiv.org. Saturation forecast: Around April 2027. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Sonnet 4.6 | Thinking, 32K | 60.1 | #179 |
| 2 | GPT-5.5 | High | 58.36 | #56 |
| 3 | Claude Opus 4.6 | Thinking, 32K | 57.29 | #114 |
| 4 | DeepSeek R1 | 56.26 | #484 | |
| 5 | ERNIE 5.0 | 56 | #469 | |
| 6 | Kimi K2.5 | 55.94 | #272 | |
| 7 | GLM-5 | 55.01 | #276 | |
| 8 | MiniMax-M2.5 | 54.14 | #600 | |
| 9 | DeepSeek V3.2 | 53.06 | #425 | |
| 10 | Qwen 3 235B A22B | 51.59 | #633 | |
| 11 | Qwen 3 32B | 36.97 | #983 | |
| 12 | Qwen 3 14B | 32.64 | #1284 | |
| 13 | Qwen 3 8B | 28.68 | #1890 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=hintbench-coarse-risk-step-localization · How It Works · Data refreshed daily, snapshot 2026-11-22.