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 GD2 (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 | 7th 77.7% | 5th 78.0% | 2nd 79.7% | 4th 78.3% | 19th 69.3% | 12th 73.7% | 17th 71.7% | 21st 67.0% | 9th 75.0% | 5th 78.0% | 10th 74.7% | 14th 73.3% | 20th 68.0% | 11th 74.0% | 3rd 79.0% | 14th 73.3% | 16th 72.3% | 1st 80.7% | 12th 73.7% | 18th 70.0% | 8th 75.3% | |
| 79.2% | 80% | 81% | 84% | 84% | 62% | 84% | 75% | 71% | 73% | 80% | 84% | 80% | 73% | 77% | 86% | 75% | 76% | 94% | 73% | 77% | 94% | |
| 69.5% | 76% | 76% | 76% | 74% | 72% | 68% | 64% | 57% | 71% | 70% | 64% | 61% | 56% | 66% | 76% | 71% | 71% | 72% | 71% | 72% | 76% | |
| 74.5% | 77% | 77% | 79% | 77% | 74% | 69% | 76% | 73% | 81% | 84% | 76% | 79% | 75% | 79% | 75% | 74% | 70% | 76% | 77% | 61% | 56% |