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 GD1 (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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 86.3% | 4th 83.0% | 3rd 83.8% | 2nd 84.5% | 13th 76.3% | 20th 72.8% | 17th 75.0% | 21st 70.5% | 8th 81.0% | 5th 82.3% | 17th 75.0% | 14th 76.3% | 11th 76.8% | 19th 74.8% | 9th 79.8% | 7th 81.8% | 12th 76.5% | 9th 79.8% | 5th 82.3% | 16th 75.5% | 15th 75.7% | |
| 68.8% | 78% | 75% | 72% | 72% | 66% | 61% | 71% | 69% | 75% | 72% | 69% | 82% | 69% | 67% | 69% | 71% | 67% | 57% | 72% | 62% | 49% | |
| 85.5% | 92% | 86% | 90% | 91% | 91% | 88% | 89% | 82% | 75% | 92% | 84% | 81% | 91% | 77% | 87% | 89% | 86% | 84% | 82% | 66% | 92% | |
| 79.2% | 86% | 89% | 88% | 87% | 80% | 66% | 63% | 66% | 87% | 85% | 66% | 66% | 66% | 78% | 79% | 85% | 76% | 90% | 92% | 90% | ||
| 80.8% | 89% | 82% | 85% | 88% | 68% | 76% | 77% | 65% | 87% | 80% | 81% | 76% | 81% | 77% | 84% | 82% | 77% | 88% | 83% | 84% | 86% |