Discrete-event world model generation on Discrete-Event World Models 7 Scenarios
7S_BCSSWE-Agent
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SWE-AgentModel Family=Large Models, Backbone=Claude 3.5 Sonnet, Interaction Mode=Iterative2026.03 | 7 | 0 | |
| SWE-Agent-LiteModel Family=Large Models, Backbone=Claude 3.5 Sonnet, Interaction Mode=Non-Iterative2026.03 | 7 | 0 | |
| SWE-AgentModel Family=Small Models, Backbone=GLM-4.7-Flash, Interaction Mode=Iterative2026.03 | 6.88 | 13 | |
| SWE-Agent-LiteModel Family=Large Models, Backbone=GPT-5.2, Interaction Mode=Non-Iterative2026.03 | 6.74 | 0 | |
| SWE-AgentModel Family=Large Models, Backbone=GLM-4.7, Interaction Mode=Iterative2026.03 | 6.46 | 61 | |
| OpenHandsModel Family=Small Models, Backbone=GLM-4.7-Flash, Interaction Mode=Iterative2026.03 | 6.46 | 41 | |
| OpenHandsModel Family=Small Models, Backbone=Llama-4-17b, Interaction Mode=Iterative2026.03 | 6.38 | 13 | |
| OpenHandsModel Family=Small Models, Backbone=Gemini 3 Flash, Interaction Mode=Iterative2026.03 | 6.36 | 91 | |
| OpenHands-LiteModel Family=Small Models, Backbone=Gemini 3 Flash, Interaction Mode=Non-Iterative2026.03 | 6.31 | 71 | |
| SWE-AgentModel Family=Small Models, Backbone=Qwen3-Coder-30b, Interaction Mode=Iterative2026.03 | 6.28 | 71 | |
| OpenHands-LiteModel Family=Small Models, Backbone=Llama-4-17b, Interaction Mode=Non-Iterative2026.03 | 5.97 | 21 | |
| SWE-AgentModel Family=Small Models, Backbone=Llama-4-17b, Interaction Mode=Iterative2026.03 | 5.95 | 21 | |
| OpenHandsModel Family=Large Models, Backbone=Claude 3.5 Sonnet, Interaction Mode=Iterative2026.03 | 5.83 | 91 | |
| OpenHandsModel Family=Small Models, Backbone=Qwen3-Coder-30b, Interaction Mode=Iterative2026.03 | 5.78 | 72 | |
| OpenHands-LiteModel Family=Large Models, Backbone=Gemini 3 Pro, Interaction Mode=Non-Iterative2026.03 | 5.77 | 76 | |
| OpenHandsModel Family=Large Models, Backbone=GLM-4.7, Interaction Mode=Iterative2026.03 | 5.71 | 86 | |
| OpenHands-LiteModel Family=Small Models, Backbone=Qwen3-Coder-30b, Interaction Mode=Non-Iterative2026.03 | 5.68 | 58 | |
| DEVS-GenModel Family=Small Models, Backbone=GLM-4.7-Flash, Interaction Mode=Non-Iterative2026.03 | 5.66 | 48 | |
| OpenHands-LiteModel Family=Large Models, Backbone=Claude 3.5 Sonnet, Interaction Mode=Non-Iterative2026.03 | 5.65 | 84 | |
| OpenHands-LiteModel Family=Small Models, Backbone=GLM-4.7-Flash, Interaction Mode=Non-Iterative2026.03 | 5.62 | 33 | |
| SWE-AgentModel Family=Large Models, Backbone=GPT-5.2, Interaction Mode=Iterative2026.03 | 5.61 | 89 | |
| SWE-AgentModel Family=Large Models, Backbone=Gemini 3 Pro, Interaction Mode=Iterative2026.03 | 5.59 | 81 | |
| OpenHandsModel Family=Large Models, Backbone=Gemini 3 Pro, Interaction Mode=Iterative2026.03 | 5.58 | 90 | |
| OpenHandsModel Family=Large Models, Backbone=GPT-5.2, Interaction Mode=Iterative2026.03 | 5.57 | 96 | |
| OpenHands-LiteModel Family=Large Models, Backbone=GLM-4.7, Interaction Mode=Non-Iterative2026.03 | 5.57 | 48 | |
| SWE-Agent-LiteModel Family=Small Models, Backbone=Qwen3-Coder-30b, Interaction Mode=Non-Iterative2026.03 | 5.51 | 33 | |
| SWE-Agent-LiteModel Family=Small Models, Backbone=Llama-4-17b, Interaction Mode=Non-Iterative2026.03 | 5.49 | 13 | |
| SWE-AgentModel Family=Small Models, Backbone=Gemini 3 Flash, Interaction Mode=Iterative2026.03 | 5.42 | 71 | |
| DEVS-GenModel Family=Large Models, Backbone=GPT-5.2, Interaction Mode=Non-Iterative2026.03 | 5.39 | 86 | |
| DEVS-GenModel Family=Large Models, Backbone=GLM-4.7, Interaction Mode=Non-Iterative2026.03 | 5.38 | 87 | |
| DEVS-GenModel Family=Large Models, Backbone=Gemini 3 Pro, Interaction Mode=Non-Iterative2026.03 | 5.37 | 80 | |
| DEVS-GenModel Family=Large Models, Backbone=Claude 3.5 Sonnet, Interaction Mode=Non-Iterative2026.03 | 5.26 | 83 | |
| DEVS-GenModel Family=Small Models, Backbone=Gemini 3 Flash, Interaction Mode=Non-Iterative2026.03 | 5.17 | 95 | |
| DEVS-GenModel Family=Small Models, Backbone=Qwen3-Coder-30b, Interaction Mode=Non-Iterative2026.03 | 5.13 | 58 | |
| OpenHands-LiteModel Family=Large Models, Backbone=GPT-5.2, Interaction Mode=Non-Iterative2026.03 | 5.07 | 93 | |
| SWE-Agent-LiteModel Family=Small Models, Backbone=GLM-4.7-Flash, Interaction Mode=Non-Iterative2026.03 | 5.05 | 18 | |
| DEVS-GenModel Family=Small Models, Backbone=Llama-4-17b, Interaction Mode=Non-Iterative2026.03 | 4.8 | 11 | |
| SWE-Agent-LiteModel Family=Large Models, Backbone=Gemini 3 Pro, Interaction Mode=Non-Iterative2026.03 | 4.69 | 82 | |
| SWE-Agent-LiteModel Family=Large Models, Backbone=GLM-4.7, Interaction Mode=Non-Iterative2026.03 | 4.63 | 44 | |
| SWE-Agent-LiteModel Family=Small Models, Backbone=Gemini 3 Flash, Interaction Mode=Non-Iterative2026.03 | 4.25 | 79 |