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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 5th 82.5% | 10th 80.3% | 3rd 83.0% | 2nd 83.3% | 11th 79.0% | 18th 72.8% | 6th 82.0% | 17th 74.3% | 20th 71.3% | 9th 80.8% | 15th 75.8% | 3rd 83.0% | 13th 77.8% | 21st 70.0% | 12th 79.0% | 19th 72.0% | 16th 74.8% | 7th 81.5% | 7th 81.5% | 1st 83.8% | 14th 76.3% | |
| 69.3% | 72% | 71% | 75% | 72% | 67% | 61% | 70% | 71% | 72% | 78% | 67% | 74% | 67% | 79% | 71% | 70% | 54% | 62% | 65% | 72% | 66% | |
| 85.9% | 96% | 97% | 86% | 88% | 89% | 88% | 84% | 86% | 88% | 75% | 89% | 89% | 89% | 77% | 90% | 81% | 85% | 83% | 90% | 88% | 66% | |
| 79.0% | 82% | 68% | 89% | 88% | 83% | 66% | 89% | 63% | 64% | 86% | 74% | 85% | 74% | 64% | 74% | 67% | 84% | 88% | 90% | 92% | 90% | |
| 78.9% | 80% | 85% | 82% | 85% | 77% | 76% | 85% | 77% | 61% | 84% | 73% | 84% | 81% | 60% | 81% | 70% | 76% | 93% | 81% | 83% | 83% |