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 | 10th 70.8% | 12th 70.5% | 13th 70.3% | 18th 68.3% | 2nd 74.8% | 19th 67.0% | 3rd 74.3% | 1st 76.5% | 7th 71.3% | 4th 73.8% | 16th 70.0% | 14th 70.3% | 8th 71.2% | 10th 70.8% | 5th 72.0% | 14th 70.3% | 17th 68.8% | 20th 66.8% | 6th 71.5% | 21st 62.0% | 9th 71.0% | |
| 62.0% | 64% | 66% | 60% | 60% | 64% | 57% | 62% | 65% | 59% | 64% | 62% | 60% | 63% | 66% | 65% | 61% | 62% | 64% | 59% | 54% | 64% | |
| 70.5% | 72% | 69% | 75% | 67% | 77% | 71% | 75% | 78% | 71% | 71% | 75% | 67% | 71% | 69% | 73% | 70% | 66% | 71% | 67% | 53% | 73% | |
| 62.8% | 64% | 64% | 72% | 72% | 70% | 56% | 64% | 68% | 64% | 68% | 56% | 64% | 59% | 55% | 68% | 67% | 59% | 54% | 64% | 51% | 60% | |
| 87.0% | 83% | 83% | 74% | 74% | 88% | 84% | 96% | 95% | 91% | 92% | 87% | 90% | 92% | 93% | 82% | 83% | 88% | 78% | 96% | 90% | 87% |