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 Israel. 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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 4th 77.3% | 13th 75.0% | 17th 73.0% | 1st 80.3% | 14th 74.7% | 21st 69.7% | 10th 75.7% | 2nd 80.0% | 20th 71.0% | 16th 73.7% | 5th 77.3% | 10th 75.7% | 19th 72.3% | 6th 77.0% | 3rd 77.7% | 8th 76.7% | 12th 75.3% | 18th 72.7% | 9th 76.3% | 6th 77.0% | 15th 74.3% | |
| 74.0% | 79% | 69% | 64% | 78% | 82% | 61% | 76% | 88% | 77% | 78% | 72% | 78% | 72% | 79% | 68% | 65% | 73% | 65% | 70% | 82% | 78% | |
| 68.1% | 73% | 74% | 75% | 75% | 68% | 74% | 72% | 64% | 61% | 63% | 70% | 70% | 60% | 62% | 77% | 75% | 59% | 67% | 70% | 61% | 61% | |
| 84.0% | 80% | 82% | 80% | 88% | 74% | 74% | 79% | 88% | 75% | 80% | 90% | 79% | 85% | 90% | 88% | 90% | 94% | 86% | 89% | 88% | 84% |