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 Egypt. 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 | 2nd 74.8% | 5th 72.8% | 7th 71.8% | 6th 72.0% | 3rd 74.3% | 19th 61.5% | 16th 64.8% | 12th 66.8% | 14th 65.8% | 11th 67.5% | 9th 70.0% | 7th 71.8% | 16th 64.8% | 10th 69.0% | 1st 75.5% | 4th 73.0% | 20th 61.3% | 13th 66.3% | 14th 65.8% | 18th 62.0% | 21st 60.8% | |
| 78.2% | 81% | 77% | 75% | 67% | 86% | 73% | 75% | 80% | 75% | 81% | 76% | 93% | 86% | 84% | 81% | 80% | 71% | 83% | 81% | 71% | 67% | |
| 70.5% | 75% | 73% | 69% | 78% | 75% | 69% | 78% | 64% | 68% | 69% | 78% | 69% | 69% | 69% | 75% | 71% | 62% | 75% | 69% | 66% | 59% | |
| 54.0% | 65% | 65% | 65% | 65% | 60% | 39% | 46% | 48% | 45% | 52% | 51% | 60% | 39% | 48% | 68% | 70% | 52% | 39% | 48% | 51% | 57% | |
| 70.0% | 78% | 76% | 78% | 78% | 76% | 65% | 60% | 75% | 75% | 68% | 75% | 65% | 65% | 75% | 78% | 71% | 60% | 68% | 65% | 60% | 60% |