Loading blueprint versions...
Please wait while we gather all the unique runs for this blueprint.
Please wait while we gather all the unique runs for this blueprint.
Please wait while we prepare the detailed comparison.
DTEF: Predict response distributions for Bangladesh. Source: Global Dialogues GD2 (https://github.com/collect-intel/global-dialogues)
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | Qwen3 30b A3B Instruct 2507 | Qwen3 Next 80b A3B Instruct | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 65.3% | 7th 61.3% | 5th 63.7% | 1st 67.7% | 13th 53.0% | 12th 55.7% | 8th 60.7% | 9th 60.3% | 4th 64.7% | 10th 57.0% | 6th 62.7% | 11th 56.7% | 1st 67.7% | |
| 67.3% | 69% | 65% | 68% | 68% | 61% | 63% | 67% | 69% | 73% | 62% | 72% | 65% | 73% | |
| 58.0% | 65% | 63% | 68% | 68% | 43% | 48% | 62% | 57% | 61% | 51% | 51% | 49% | 68% | |
| 58.5% | 62% | 56% | 55% | 67% | 55% | 56% | 53% | 55% | 60% | 58% | 65% | 56% | 62% |