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 | 1st 86.0% | 11th 79.8% | 5th 83.0% | 3rd 83.5% | 10th 80.0% | 14th 77.5% | 8th 81.0% | 17th 75.0% | 20th 69.5% | 7th 81.5% | 18th 74.8% | 2nd 83.7% | 13th 77.5% | 19th 73.8% | 9th 80.3% | 16th 75.8% | 15th 77.0% | 12th 78.8% | 21st 42.8% | 3rd 83.5% | 6th 81.8% | |
| 66.9% | 71% | 62% | 75% | 72% | 67% | 61% | 68% | 71% | 69% | 78% | 69% | 72% | 67% | 92% | 71% | 75% | 56% | 58% | 10% | 75% | 65% | |
| 84.6% | 98% | 83% | 86% | 89% | 87% | 87% | 81% | 89% | 83% | 75% | 85% | 94% | 88% | 77% | 85% | 81% | 85% | 82% | 79% | 82% | 81% | |
| 76.3% | 90% | 89% | 89% | 88% | 83% | 84% | 90% | 63% | 65% | 87% | 59% | 85% | 73% | 49% | 81% | 66% | 86% | 87% | 0% | 90% | 98% | |
| 82.0% | 85% | 85% | 82% | 85% | 83% | 78% | 85% | 77% | 61% | 86% | 86% | 84% | 82% | 77% | 84% | 81% | 81% | 88% | 82% | 87% | 83% |