Aspect-level pluralism evaluation on Reval book reviews (evaluation)
97.9CoverageGemini 2.5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Gemini 2.5Setup=Personas2026.06 | 97.9 | 0.12 | |
| Llama 3.1 8BSetup=Personas2026.06 | 92.2 | 0.17 | |
| OLMo2 1BSetup=t = 1.52026.06 | 83.8 | 0.21 | |
| Gemini 2.5Setup=t = 1.52026.06 | 76.9 | 0.21 | |
| Llama 3.1 8BSetup=t = 1.52026.06 | 76.1 | 0.23 | |
| OLMo2 1BSetup=Personas2026.06 | 75.6 | 0.23 | |
| OLMo2 7BSetup=t = 1.52026.06 | 74.4 | 0.24 | |
| OLMo2 1BSetup=t = 0.72026.06 | 72.7 | 0.23 | |
| Gemini 2.5Setup=t = 0.72026.06 | 71.8 | 0.22 | |
| OLMo2 7BSetup=Personas2026.06 | 69.1 | 0.24 | |
| GPT 4.1Setup=Personas2026.06 | 65.5 | 0.26 | |
| Llama 3.1 8BSetup=t = 0.72026.06 | 63.8 | 0.25 | |
| OLMo2 7BSetup=t = 0.72026.06 | 59.3 | 0.27 | |
| GPT 4.1Setup=t = 1.52026.06 | 51.9 | 0.3 | |
| GPT 4.1Setup=t = 0.72026.06 | 41.4 | 0.33 |