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 Philippines. 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 | 6th 76.8% | 7th 76.8% | 9th 75.5% | 9th 75.5% | 5th 77.3% | 16th 72.5% | 4th 78.0% | 15th 73.0% | 12th 74.5% | 3rd 78.3% | 11th 74.8% | 19th 70.0% | 7th 76.8% | 20th 69.8% | 17th 71.7% | 1st 78.8% | 18th 71.2% | 14th 73.3% | 13th 73.5% | 2nd 78.5% | 21st 65.0% | |
| 52.1% | 55% | 54% | 55% | 55% | 50% | 48% | 60% | 54% | 61% | 61% | 49% | 46% | 54% | 53% | 51% | 58% | 43% | 44% | 51% | 46% | 46% | |
| 80.2% | 84% | 84% | 78% | 84% | 97% | 81% | 85% | 74% | 69% | 83% | 84% | 74% | 95% | 78% | 69% | 81% | 83% | 83% | 78% | 95% | 46% | |
| 82.3% | 85% | 84% | 86% | 79% | 85% | 76% | 83% | 85% | 83% | 85% | 81% | 76% | 73% | 71% | 85% | 92% | 75% | 82% | 89% | 88% | 86% | |
| 82.7% | 83% | 85% | 83% | 84% | 77% | 85% | 84% | 79% | 85% | 84% | 85% | 84% | 85% | 77% | 82% | 84% | 84% | 84% | 76% | 85% | 82% |