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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 19th 68.5% | 13th 70.5% | 7th 72.5% | 14th 70.3% | 1st 76.8% | 17th 69.5% | 2nd 75.3% | 3rd 74.8% | 9th 72.0% | 4th 74.3% | 11th 71.0% | 5th 73.0% | 8th 72.2% | 6th 72.5% | 10th 72.0% | 15th 70.3% | 21st 65.0% | 12th 70.8% | 16th 70.0% | 18th 69.0% | 20th 67.8% | |
| 62.7% | 64% | 66% | 60% | 60% | 64% | 59% | 66% | 65% | 61% | 64% | 65% | 66% | 67% | 66% | 66% | 60% | 53% | 67% | 59% | 58% | 60% | |
| 70.6% | 72% | 69% | 67% | 75% | 77% | 71% | 75% | 71% | 72% | 73% | 73% | 72% | 71% | 69% | 73% | 70% | 64% | 72% | 67% | 67% | 63% | |
| 63.7% | 64% | 64% | 72% | 72% | 73% | 56% | 64% | 68% | 64% | 68% | 59% | 64% | 59% | 58% | 70% | 66% | 55% | 57% | 64% | 59% | 62% | |
| 88.3% | 74% | 83% | 91% | 74% | 93% | 92% | 96% | 95% | 91% | 92% | 87% | 90% | 92% | 97% | 79% | 85% | 88% | 87% | 90% | 92% | 86% |