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 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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 18th 76.0% | 8th 80.3% | 16th 77.5% | 12th 78.3% | 14th 77.8% | 13th 78.0% | 15th 77.8% | 19th 75.8% | 21st 75.3% | 16th 77.5% | 2nd 84.0% | 6th 82.0% | 4th 82.0% | 4th 82.0% | 1st 84.5% | 7th 81.8% | 9th 80.3% | 10th 79.0% | 3rd 82.3% | 11th 78.5% | 20th 75.3% | |
| 78.9% | 73% | 76% | 70% | 75% | 67% | 68% | 70% | 77% | 76% | 75% | 84% | 96% | 84% | 90% | 86% | 80% | 83% | 81% | 83% | 84% | ||
| 82.9% | 68% | 88% | 80% | 82% | 76% | 94% | 88% | 75% | 71% | 75% | 90% | 78% | 91% | 80% | 88% | 87% | 82% | 94% | 87% | 83% | 83% | |
| 66.3% | 72% | 72% | 71% | 67% | 71% | 61% | 61% | 56% | 62% | 68% | 70% | 60% | 68% | 60% | 72% | 66% | 62% | 65% | 70% | 71% | 67% | |
| 89.4% | 91% | 85% | 89% | 89% | 97% | 89% | 92% | 95% | 92% | 92% | 92% | 94% | 85% | 98% | 92% | 94% | 94% | 76% | 89% | 76% | 76% |