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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 6th 77.7% | 11th 74.7% | 13th 73.3% | 1st 80.3% | 8th 76.7% | 19th 70.0% | 10th 76.0% | 1st 80.3% | 18th 70.3% | 17th 72.3% | 3rd 79.7% | 21st 68.0% | 12th 74.0% | 15th 72.7% | 4th 79.3% | 13th 73.3% | 8th 76.7% | 7th 76.7% | 5th 78.7% | 16th 72.7% | 20th 69.7% | |
| 74.0% | 82% | 69% | 64% | 78% | 82% | 61% | 76% | 89% | 76% | 78% | 70% | 81% | 79% | 66% | 77% | 70% | 79% | 74% | 70% | 72% | 60% | |
| 67.7% | 73% | 73% | 76% | 75% | 68% | 75% | 73% | 64% | 60% | 62% | 73% | 57% | 58% | 62% | 74% | 69% | 63% | 65% | 77% | 60% | 64% | |
| 83.1% | 78% | 82% | 80% | 88% | 80% | 74% | 79% | 88% | 75% | 77% | 96% | 66% | 85% | 90% | 87% | 81% | 88% | 91% | 89% | 86% | 85% |