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 Kenya. 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 | 5th 67.3% | 2nd 69.7% | 1st 70.7% | 3rd 68.0% | 13th 55.3% | 9th 63.0% | 6th 67.3% | 3rd 68.0% | 7th 63.7% | 11th 59.0% | 12th 57.3% | 9th 63.0% | 8th 63.3% | |
| 70.5% | 76% | 84% | 81% | 75% | 61% | 61% | 71% | 70% | 76% | 62% | 62% | 67% | 70% | |
| 57.0% | 60% | 60% | 64% | 65% | 46% | 59% | 61% | 65% | 50% | 46% | 45% | 59% | 61% | |
| 65.4% | 66% | 65% | 67% | 64% | 59% | 69% | 70% | 69% | 65% | 69% | 65% | 63% | 59% |