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 75.3% | 1st 77.0% | 9th 71.5% | 11th 70.8% | 5th 74.8% | 19th 64.5% | 6th 74.5% | 14th 69.3% | 12th 70.0% | 17th 68.3% | 3rd 75.8% | 10th 71.3% | 2nd 76.5% | 14th 69.3% | 12th 70.0% | 8th 73.3% | 16th 69.0% | 18th 67.7% | 21st 54.3% | 7th 73.8% | 20th 64.3% | |
| 66.8% | 67% | 66% | 65% | 60% | 60% | 54% | 73% | 66% | 67% | 65% | 74% | 74% | 76% | 70% | 72% | 77% | 65% | 57% | 75% | 64% | 55% | |
| 75.4% | 84% | 84% | 73% | 77% | 77% | 69% | 77% | 77% | 72% | 67% | 82% | 76% | 80% | 72% | 78% | 67% | 71% | 71% | 75% | 78% | 76% | |
| 63.7% | 68% | 74% | 68% | 72% | 71% | 56% | 68% | 63% | 57% | 59% | 67% | 64% | 68% | 51% | 59% | 65% | 59% | 59% | 67% | 68% | 55% | |
| 76.2% | 82% | 84% | 80% | 74% | 91% | 79% | 80% | 71% | 84% | 82% | 80% | 71% | 82% | 84% | 71% | 84% | 81% | 84% | 0% | 85% | 71% |