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 | 5th 82.8% | 4th 83.0% | 1st 84.0% | 6th 82.2% | 17th 74.8% | 21st 72.8% | 16th 75.0% | 19th 73.8% | 10th 80.5% | 8th 81.3% | 13th 78.0% | 17th 74.8% | 15th 75.5% | 14th 75.8% | 12th 79.8% | 6th 82.2% | 20th 73.0% | 3rd 83.3% | 9th 80.8% | 11th 80.3% | 2nd 83.3% | |
| 70.3% | 68% | 75% | 72% | 72% | 66% | 61% | 71% | 70% | 73% | 71% | 75% | 82% | 67% | 75% | 66% | 70% | 67% | 67% | 72% | 65% | 71% | |
| 86.2% | 92% | 86% | 88% | 93% | 82% | 88% | 89% | 83% | 75% | 90% | 88% | 77% | 86% | 81% | 90% | 89% | 84% | 92% | 77% | 86% | 95% | |
| 78.3% | 84% | 89% | 88% | 82% | 83% | 66% | 63% | 72% | 87% | 84% | 74% | 64% | 68% | 66% | 78% | 88% | 65% | 90% | 91% | 85% | ||
| 80.4% | 87% | 82% | 88% | 82% | 68% | 76% | 77% | 70% | 87% | 80% | 75% | 76% | 81% | 81% | 85% | 82% | 76% | 84% | 83% | 85% | 84% |