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 | 2nd 72.0% | 7th 69.3% | 4th 70.0% | 4th 70.0% | 1st 72.3% | 20th 61.5% | 18th 62.2% | 19th 61.7% | 10th 65.3% | 9th 68.8% | 7th 69.3% | 11th 65.3% | 14th 63.8% | 12th 65.0% | 6th 69.5% | 3rd 71.3% | 13th 64.3% | 15th 63.5% | 15th 63.5% | 21st 56.8% | 17th 63.0% | |
| 51.2% | 55% | 54% | 51% | 51% | 55% | 52% | 51% | 51% | 49% | 55% | 51% | 54% | 51% | 55% | 49% | 51% | 50% | 48% | 47% | 45% | 51% | |
| 71.1% | 78% | 71% | 71% | 71% | 84% | 63% | 71% | 71% | 65% | 78% | 78% | 71% | 70% | 71% | 73% | 78% | 68% | 67% | 67% | 61% | 67% | |
| 68.3% | 70% | 74% | 73% | 73% | 73% | 53% | 68% | 49% | 71% | 70% | 70% | 71% | 68% | 60% | 78% | 78% | 73% | 62% | 74% | 63% | 63% | |
| 73.7% | 85% | 78% | 85% | 85% | 77% | 78% | 59% | 76% | 76% | 72% | 78% | 65% | 66% | 74% | 78% | 78% | 66% | 77% | 66% | 58% | 71% |