EnvSimBench - Difficult: leaderboard
The Difficult tier of EnvSimBench (2026): 50 tool calls whose correct outcome changes 7 to 12 changed state fields of the environment state. The model sees the state, the action and its code and must predict the resulting state; the score is Config Match, the percent of samples reproduced exactly, with non-thinking mode throughout; higher is better.
Metric: Config Match (%): share of the 50 Difficult state-changing samples (7 to 12 changed state fields) whose predicted state changes, applied to the before-state, reproduce the executor after-state exactly; MDP prompt with the state, the action and its code, non-thinking mode; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GLM-5 | Non-reasoning | 28 | #276 |
| 2 | GPT-5.4 | Non-reasoning | 26 | #138 |
| 3 | Qwen 3.5 397B A17B | Non-reasoning | 24 | #270 |
| 4 | MiniMax-M2.7 | 22 | #539 | |
| 5 | Qwen 3.5 9B | Non-reasoning | 20 | #838 |
| 6 | Gemini 3.1 Pro (Preview) | 18 | #102 | |
| 7 | Claude Sonnet 4.6 | 16 | #179 | |
| 8 | Qwen 3.5 4B | Non-reasoning | 6 | #1270 |
| 9 | DeepSeek V3.2 | Non-reasoning | 4 | #425 |
| 10 | Qwen 3.5 27B | Non-reasoning | 4 | #380 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=envsimbench-difficult · How It Works · Data refreshed daily, snapshot 2026-11-22.