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 | 20th 74.7% | 2nd 79.3% | 11th 76.7% | 7th 78.7% | 13th 76.3% | 6th 79.0% | 14th 76.0% | 10th 77.3% | 11th 76.7% | 9th 77.7% | 15th 75.7% | 8th 78.3% | 2nd 79.3% | 20th 74.7% | 15th 75.7% | 2nd 79.3% | 17th 75.0% | 17th 75.0% | 2nd 79.3% | 17th 75.0% | 1st 81.0% | |
| 74.4% | 64% | 67% | 65% | 67% | 67% | 79% | 85% | 81% | 77% | 77% | 70% | 82% | 82% | 66% | 73% | 74% | 74% | 69% | 76% | 82% | 85% | |
| 73.7% | 75% | 85% | 85% | 85% | 79% | 79% | 63% | 61% | 73% | 77% | 69% | 62% | 67% | 67% | 80% | 79% | 65% | 76% | 79% | 66% | 75% | |
| 83.5% | 85% | 86% | 80% | 84% | 83% | 79% | 80% | 90% | 80% | 79% | 88% | 91% | 89% | 91% | 74% | 85% | 86% | 80% | 83% | 77% | 83% |