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 Mexico. 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 75.8% | 8th 72.8% | 11th 72.0% | 4th 74.5% | 18th 69.3% | 21st 65.3% | 16th 70.5% | 14th 71.0% | 9th 72.5% | 13th 71.5% | 3rd 74.8% | 10th 72.2% | 15th 70.8% | 5th 74.3% | 6th 74.0% | 11th 72.0% | 19th 69.0% | 7th 73.0% | 1st 76.0% | 20th 67.8% | 16th 70.5% | |
| 68.8% | 67% | 65% | 65% | 60% | 60% | 57% | 66% | 69% | 72% | 74% | 76% | 77% | 77% | 77% | 73% | 64% | 64% | 72% | 73% | 62% | 74% | |
| 75.9% | 84% | 78% | 77% | 84% | 75% | 69% | 80% | 68% | 71% | 78% | 73% | 77% | 78% | 74% | 78% | 75% | 71% | 74% | 78% | 75% | 76% | |
| 64.6% | 72% | 68% | 72% | 72% | 71% | 56% | 65% | 63% | 59% | 64% | 68% | 51% | 59% | 65% | 67% | 67% | 60% | 63% | 71% | 63% | 61% | |
| 78.2% | 80% | 80% | 74% | 82% | 71% | 79% | 71% | 84% | 88% | 70% | 82% | 84% | 69% | 81% | 78% | 82% | 81% | 83% | 82% | 71% | 71% |