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 | 7th 81.5% | 5th 83.0% | 2nd 83.3% | 1st 85.0% | 13th 77.5% | 19th 72.8% | 18th 74.3% | 21st 70.3% | 9th 80.0% | 2nd 83.3% | 15th 75.8% | 20th 72.0% | 17th 74.8% | 16th 75.3% | 8th 81.3% | 6th 82.0% | 14th 76.0% | 12th 78.5% | 2nd 83.3% | 11th 78.8% | 10th 79.0% | |
| 69.2% | 72% | 75% | 72% | 75% | 66% | 61% | 71% | 68% | 73% | 73% | 71% | 78% | 67% | 75% | 68% | 69% | 58% | 58% | 72% | 66% | 66% | |
| 85.9% | 89% | 86% | 88% | 92% | 91% | 88% | 86% | 85% | 74% | 93% | 88% | 77% | 82% | 83% | 87% | 91% | 76% | 86% | 88% | 82% | 91% | |
| 79.1% | 80% | 89% | 88% | 85% | 83% | 66% | 63% | 67% | 87% | 87% | 69% | 64% | 73% | 66% | 87% | 86% | 86% | 86% | 92% | 84% | 73% | |
| 79.6% | 85% | 82% | 85% | 88% | 70% | 76% | 77% | 61% | 86% | 80% | 75% | 69% | 77% | 77% | 83% | 82% | 84% | 84% | 81% | 83% | 86% |