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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 9th 77.0% | 4th 81.0% | 2nd 81.7% | 10th 76.7% | 17th 71.0% | 17th 71.0% | 20th 68.0% | 21st 62.3% | 3rd 81.3% | 5th 80.0% | 19th 70.0% | 8th 77.3% | 14th 74.3% | 15th 74.0% | 7th 77.7% | 13th 74.7% | 6th 79.3% | 12th 75.7% | 1st 86.7% | 11th 76.3% | 16th 71.3% | |
| 85.0% | 84% | 85% | 93% | 93% | 63% | 82% | 77% | 67% | 92% | 84% | 80% | 97% | 85% | 81% | 87% | 83% | 91% | 84% | 93% | 87% | 97% | |
| 74.2% | 75% | 85% | 84% | 64% | 87% | 64% | 58% | 52% | 80% | 84% | 60% | 61% | 63% | 76% | 77% | 73% | 86% | 82% | 94% | 82% | 71% | |
| 67.6% | 72% | 73% | 68% | 73% | 63% | 67% | 69% | 68% | 72% | 72% | 70% | 74% | 75% | 65% | 69% | 68% | 61% | 61% | 73% | 60% | 46% |