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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 4th 74.0% | 3rd 75.0% | 12th 71.5% | 10th 72.0% | 1st 78.3% | 21st 65.3% | 6th 73.8% | 17th 69.8% | 8th 72.8% | 20th 66.5% | 4th 74.0% | 16th 70.0% | 2nd 77.5% | 14th 70.8% | 18th 68.5% | 8th 72.8% | 13th 71.0% | 11th 71.8% | 7th 73.3% | 15th 70.0% | 19th 67.3% | |
| 68.9% | 64% | 64% | 65% | 65% | 67% | 57% | 74% | 66% | 67% | 69% | 76% | 74% | 76% | 70% | 72% | 77% | 66% | 67% | 79% | 64% | 67% | |
| 75.3% | 82% | 84% | 73% | 77% | 84% | 69% | 76% | 77% | 72% | 67% | 84% | 71% | 82% | 78% | 72% | 71% | 71% | 74% | 73% | 77% | 67% | |
| 63.3% | 68% | 68% | 68% | 72% | 71% | 56% | 65% | 65% | 62% | 59% | 65% | 64% | 68% | 51% | 59% | 58% | 59% | 63% | 57% | 68% | 64% | |
| 79.3% | 82% | 84% | 80% | 74% | 91% | 79% | 80% | 71% | 90% | 71% | 71% | 71% | 84% | 84% | 71% | 85% | 88% | 83% | 84% | 71% | 71% |