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 | 2nd 79.0% | 7th 76.3% | 9th 76.0% | 3rd 78.3% | 13th 72.7% | 18th 71.3% | 15th 71.7% | 21st 67.3% | 11th 74.7% | 7th 76.3% | 15th 71.7% | 19th 71.0% | 20th 67.3% | 12th 74.0% | 6th 76.7% | 5th 77.3% | 17th 71.7% | 13th 72.7% | 10th 75.3% | 3rd 78.3% | 1st 81.3% | |
| 78.3% | 83% | 81% | 84% | 84% | 62% | 84% | 75% | 71% | 73% | 80% | 75% | 73% | 71% | 77% | 80% | 83% | 71% | 77% | 73% | 94% | 94% | |
| 70.6% | 77% | 71% | 70% | 74% | 77% | 61% | 64% | 57% | 70% | 70% | 64% | 61% | 56% | 66% | 77% | 72% | 73% | 75% | 76% | 78% | 94% | |
| 74.0% | 77% | 77% | 74% | 77% | 79% | 69% | 76% | 74% | 81% | 79% | 76% | 79% | 75% | 79% | 73% | 77% | 71% | 66% | 77% | 63% | 56% |