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 | 8th 76.8% | 2nd 79.8% | 12th 74.5% | 5th 77.5% | 17th 71.0% | 11th 74.8% | 4th 78.5% | 18th 70.8% | 10th 75.0% | 3rd 78.5% | 13th 74.3% | 20th 70.0% | 7th 77.0% | 19th 70.2% | 16th 72.5% | 9th 76.5% | 6th 77.3% | 13th 74.3% | 15th 74.0% | 1st 91.0% | 21st 67.3% | |
| 53.5% | 62% | 60% | 51% | 55% | 49% | 54% | 62% | 57% | 61% | 61% | 49% | 46% | 52% | 53% | 53% | 51% | 51% | 41% | 55% | 46% | ||
| 81.2% | 78% | 84% | 78% | 84% | 79% | 84% | 85% | 74% | 71% | 83% | 84% | 74% | 95% | 78% | 72% | 85% | 97% | 83% | 74% | 82% | ||
| 82.1% | 83% | 90% | 86% | 86% | 85% | 76% | 83% | 73% | 83% | 85% | 79% | 76% | 76% | 70% | 80% | 85% | 78% | 96% | 89% | 91% | 74% | |
| 83.3% | 84% | 85% | 83% | 85% | 71% | 85% | 84% | 79% | 85% | 85% | 85% | 84% | 85% | 80% | 85% | 85% | 83% | 77% | 78% | 100% | 82% |