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 | 3rd 71.8% | 5th 69.8% | 2nd 73.3% | 8th 69.0% | 1st 74.0% | 19th 61.5% | 18th 62.2% | 17th 62.3% | 13th 64.8% | 9th 66.3% | 7th 69.3% | 11th 65.3% | 21st 59.8% | 12th 65.0% | 4th 71.5% | 6th 69.5% | 14th 64.5% | 15th 63.8% | 9th 66.3% | 20th 60.3% | 16th 63.0% | |
| 51.9% | 51% | 54% | 51% | 54% | 55% | 52% | 51% | 55% | 45% | 55% | 51% | 54% | 51% | 55% | 54% | 52% | 50% | 50% | 51% | 48% | 51% | |
| 71.3% | 77% | 71% | 84% | 71% | 84% | 63% | 71% | 71% | 65% | 71% | 83% | 71% | 70% | 71% | 78% | 74% | 66% | 66% | 67% | 62% | 61% | |
| 67.3% | 74% | 74% | 73% | 73% | 73% | 53% | 68% | 47% | 73% | 67% | 58% | 71% | 55% | 60% | 76% | 75% | 70% | 62% | 74% | 64% | 74% | |
| 74.8% | 85% | 80% | 85% | 78% | 84% | 78% | 59% | 76% | 76% | 72% | 85% | 65% | 63% | 74% | 78% | 77% | 72% | 77% | 73% | 67% | 66% |