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 76.5% | 7th 70.0% | 2nd 75.8% | 3rd 75.3% | 5th 71.3% | 19th 60.8% | 10th 65.5% | 18th 62.2% | 10th 65.5% | 6th 70.8% | 12th 65.0% | 16th 63.7% | 8th 66.3% | 17th 63.2% | 20th 57.5% | 4th 75.0% | 15th 64.0% | 13th 64.5% | 9th 66.0% | 20th 57.5% | 14th 64.3% | |
| 63.8% | 72% | 68% | 68% | 69% | 66% | 61% | 70% | 69% | 60% | 70% | 67% | 71% | 67% | 71% | 0% | 73% | 59% | 67% | 64% | 60% | 68% | |
| 78.2% | 91% | 76% | 89% | 89% | 85% | 74% | 76% | 71% | 72% | 78% | 80% | 77% | 78% | 76% | 84% | 84% | 73% | 77% | 72% | 67% | 74% | |
| 59.8% | 63% | 64% | 66% | 67% | 68% | 49% | 62% | 49% | 66% | 69% | 48% | 48% | 60% | 47% | 71% | 71% | 64% | 46% | 63% | 56% | 59% | |
| 64.9% | 80% | 72% | 80% | 76% | 66% | 59% | 54% | 60% | 64% | 66% | 65% | 59% | 60% | 59% | 75% | 72% | 60% | 68% | 65% | 47% | 56% |