Essay Grading on Essay Grading (test)
0.53NMSEMENTATBasic Prompt
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MENTATBasic PromptLM=GPT-4.1, Training Size=5002025.08 | 0.53 | 0.68 | |
| MENTATBasic PromptLM=GPT-4.1, Training Size=1002025.08 | 0.54 | 0.7 | |
| MENTAT-AvgLM=GPT-4.1, Training Size=1002025.08 | 0.57 | 0.69 | |
| MENTAT PromptLM=GPT-4.1, Training Size=1002025.08 | 0.61 | 0.68 | |
| MENTAT-AvgLM=GPT-4.1, Training Size=5002025.08 | 0.63 | 0.68 | |
| MENTATBasic PromptLM=GPT-5, Training Size=1002025.08 | 0.64 | 0.59 | |
| MENTATBasic PromptLM=GPT-5, Training Size=5002025.08 | 0.67 | 0.55 | |
| MENTAT-AvgLM=GPT-5, Training Size=5002025.08 | 0.67 | 0.55 | |
| MENTAT-AvgLM=GPT-5, Training Size=1002025.08 | 0.69 | 0.57 | |
| MENTAT PromptLM=GPT-5, Training Size=5002025.08 | 0.7 | 0.54 | |
| MENTAT PromptLM=GPT-4.1, Training Size=5002025.08 | 0.71 | 0.66 | |
| Detailed PromptLM=GPT-4.1, Training Size=1002025.08 | 0.73 | 0.65 | |
| Detailed PromptLM=GPT-4.1, Training Size=5002025.08 | 0.73 | 0.65 | |
| MENTAT PromptLM=GPT-5, Training Size=1002025.08 | 0.74 | 0.57 | |
| Basic PromptLM=GPT-4.1, Training Size=1002025.08 | 0.75 | 0.63 | |
| Basic PromptLM=GPT-4.1, Training Size=5002025.08 | 0.75 | 0.63 | |
| GEPALM=GPT-4.1, Training Size=1002025.08 | 0.79 | 0.63 | |
| GEPALM=GPT-4.1, Training Size=5002025.08 | 0.81 | 0.63 | |
| Gradient DescentLM=NeoBERT, Training Size=5002025.08 | 0.91 | 0.65 | |
| GEPALM=GPT-5, Training Size=1002025.08 | 1.01 | 0.42 | |
| GEPALM=GPT-5, Training Size=5002025.08 | 1.01 | 0.44 | |
| Gradient DescentLM=NeoBERT, Training Size=1002025.08 | 1.03 | 0.19 | |
| Basic PromptLM=GPT-5, Training Size=1002025.08 | 1.31 | 0.42 | |
| Basic PromptLM=GPT-5, Training Size=5002025.08 | 1.31 | 0.42 | |
| Detailed PromptLM=GPT-5, Training Size=1002025.08 | 1.53 | 0.4 | |
| Detailed PromptLM=GPT-5, Training Size=5002025.08 | 1.53 | 0.4 |