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 Morocco. Source: Global Dialogues GD1 (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 69.3% | 4th 68.8% | 7th 65.0% | 1st 75.5% | 13th 54.0% | 10th 58.7% | 5th 66.8% | 6th 65.8% | 8th 64.0% | 12th 57.8% | 9th 63.0% | 11th 58.5% | 2nd 72.3% | |
| 66.3% | 65% | 62% | 62% | 75% | 52% | 64% | 70% | 73% | 71% | 62% | 75% | 58% | 73% | |
| 68.8% | 70% | 70% | 71% | 84% | 66% | 70% | 65% | 65% | 67% | 61% | 67% | 66% | 72% | |
| 60.8% | 71% | 71% | 71% | 71% | 42% | 49% | 68% | 64% | 54% | 52% | 52% | 54% | 71% | |
| 62.4% | 71% | 72% | 56% | 72% | 56% | 52% | 64% | 61% | 64% | 56% | 58% | 56% | 73% |