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% | 3rd 83.0% | 3rd 83.0% | 3rd 83.0% | 21st 72.0% | 19th 72.5% | 15th 75.0% | 18th 72.7% | 8th 80.5% | 2nd 83.3% | 11th 78.5% | 19th 72.5% | 13th 77.8% | 17th 74.5% | 9th 80.3% | 9th 80.3% | 12th 78.3% | 14th 76.8% | 6th 82.8% | 16th 74.8% | 7th 82.2% | |
| 69.2% | 74% | 75% | 71% | 69% | 67% | 61% | 71% | 73% | 73% | 73% | 69% | 71% | 71% | 70% | 72% | 68% | 67% | 56% | 72% | 65% | 66% | |
| 85.4% | 94% | 86% | 88% | 93% | 81% | 87% | 89% | 82% | 75% | 93% | 88% | 77% | 88% | 86% | 85% | 86% | 86% | 87% | 82% | 66% | 95% | |
| 79.4% | 91% | 89% | 88% | 82% | 80% | 66% | 63% | 67% | 87% | 87% | 74% | 66% | 68% | 65% | 80% | 82% | 83% | 87% | 90% | 88% | 84% | |
| 80.2% | 86% | 82% | 85% | 88% | 60% | 76% | 77% | 69% | 87% | 80% | 83% | 76% | 84% | 77% | 84% | 85% | 77% | 77% | 87% | 80% | 84% |