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 | 5th 75.3% | 8th 73.8% | 11th 72.8% | 10th 73.0% | 7th 74.0% | 21st 65.3% | 9th 73.5% | 13th 70.5% | 13th 70.5% | 19th 66.5% | 1st 82.5% | 15th 70.3% | 4th 75.5% | 12th 72.2% | 15th 70.3% | 3rd 76.0% | 17th 68.3% | 20th 66.0% | 2nd 79.0% | 6th 75.0% | 18th 66.8% | |
| 68.3% | 67% | 66% | 65% | 62% | 67% | 57% | 73% | 66% | 67% | 65% | 76% | 74% | 73% | 77% | 77% | 77% | 67% | 53% | 79% | 64% | 62% | |
| 76.7% | 84% | 82% | 78% | 84% | 75% | 69% | 77% | 80% | 72% | 71% | 98% | 76% | 77% | 77% | 77% | 71% | 70% | 72% | 78% | 73% | 70% | |
| 63.6% | 68% | 63% | 68% | 72% | 63% | 56% | 65% | 65% | 59% | 59% | 76% | 60% | 68% | 51% | 56% | 65% | 55% | 64% | 67% | 71% | 64% | |
| 80.3% | 82% | 84% | 80% | 74% | 91% | 79% | 79% | 71% | 84% | 71% | 80% | 71% | 84% | 84% | 71% | 91% | 81% | 75% | 92% | 92% | 71% |