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 3.7 Sonnet | Claude Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT 5 | GPT 5.1 | GPT OSS 120b | GPT OSS 20b | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | Grok 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 9th 76.3% | 4th 80.7% | 6th 79.7% | 11th 75.0% | 13th 73.3% | 18th 69.7% | 20th 67.7% | 21st 64.7% | 3rd 81.3% | 10th 75.3% | 15th 71.7% | 12th 74.0% | 15th 71.7% | 19th 69.3% | 4th 80.7% | 7th 77.0% | 15th 71.7% | 7th 77.0% | 1st 83.7% | 14th 73.0% | 2nd 83.0% | |
| 83.7% | 84% | 84% | 90% | 93% | 63% | 82% | 76% | 62% | 92% | 80% | 83% | 91% | 84% | 81% | 86% | 83% | 87% | 88% | 93% | 81% | 94% | |
| 74.4% | 74% | 85% | 81% | 65% | 85% | 63% | 58% | 63% | 80% | 77% | 63% | 61% | 62% | 63% | 86% | 82% | 71% | 82% | 86% | 84% | 91% | |
| 67.1% | 71% | 73% | 68% | 67% | 72% | 64% | 69% | 69% | 72% | 69% | 69% | 70% | 69% | 64% | 70% | 66% | 57% | 61% | 72% | 54% | 64% |