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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 4th 74.5% | 8th 69.3% | 3rd 75.3% | 1st 76.3% | 5th 74.5% | 19th 60.5% | 13th 65.0% | 17th 62.0% | 15th 63.5% | 7th 70.8% | 11th 66.0% | 10th 66.3% | 9th 66.3% | 16th 63.0% | 6th 72.5% | 1st 76.3% | 14th 64.0% | 20th 60.0% | 12th 65.8% | 21st 59.8% | 17th 62.0% | |
| 66.4% | 68% | 68% | 68% | 69% | 66% | 61% | 70% | 69% | 60% | 69% | 67% | 80% | 66% | 69% | 70% | 71% | 57% | 65% | 65% | 59% | 58% | |
| 77.3% | 87% | 73% | 89% | 89% | 85% | 74% | 74% | 72% | 72% | 86% | 78% | 78% | 79% | 76% | 84% | 85% | 72% | 67% | 72% | 67% | 64% | |
| 59.3% | 63% | 64% | 64% | 67% | 76% | 49% | 60% | 48% | 55% | 62% | 53% | 48% | 60% | 48% | 67% | 75% | 64% | 38% | 62% | 55% | 68% | |
| 66.1% | 80% | 72% | 80% | 80% | 71% | 58% | 56% | 59% | 67% | 66% | 66% | 59% | 60% | 59% | 69% | 74% | 63% | 70% | 64% | 58% | 58% |