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 GD2 (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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 5th 81.0% | 9th 79.3% | 2nd 82.3% | 4th 82.0% | 11th 78.7% | 21st 74.0% | 16th 76.0% | 18th 75.0% | 7th 80.3% | 2nd 82.3% | 10th 79.0% | 12th 78.0% | 13th 77.0% | 17th 75.3% | 1st 83.3% | 15th 76.7% | 8th 79.7% | 13th 77.0% | 5th 81.0% | 20th 74.3% | 19th 74.7% | |
| 84.9% | 87% | 83% | 87% | 87% | 81% | 83% | 87% | 84% | 88% | 94% | 87% | 85% | 87% | 87% | 83% | 83% | 87% | 77% | 87% | 82% | 76% | |
| 60.8% | 65% | 64% | 72% | 63% | 68% | 59% | 48% | 51% | 58% | 57% | 59% | 62% | 53% | 55% | 72% | 59% | 60% | 63% | 64% | 58% | 67% | |
| 89.6% | 91% | 91% | 88% | 96% | 87% | 80% | 93% | 90% | 95% | 96% | 91% | 87% | 91% | 84% | 95% | 88% | 92% | 91% | 92% | 83% | 81% |