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 | 15th 77.8% | 8th 80.3% | 20th 75.8% | 13th 78.3% | 10th 78.8% | 16th 77.5% | 11th 78.5% | 17th 77.3% | 21st 74.8% | 14th 78.0% | 4th 83.5% | 11th 78.5% | 18th 76.5% | 7th 82.0% | 3rd 84.5% | 1st 84.8% | 2nd 84.5% | 6th 82.5% | 5th 82.8% | 9th 80.0% | 19th 76.3% | |
| 79.2% | 75% | 76% | 70% | 75% | 72% | 68% | 70% | 81% | 76% | 76% | 85% | 77% | 84% | 90% | 82% | 85% | 89% | 86% | 83% | 81% | 83% | |
| 84.0% | 73% | 88% | 80% | 82% | 80% | 92% | 88% | 76% | 71% | 76% | 94% | 83% | 80% | 80% | 89% | 89% | 94% | 91% | 87% | 87% | 83% | |
| 66.5% | 71% | 72% | 71% | 67% | 71% | 61% | 64% | 55% | 60% | 68% | 70% | 60% | 57% | 60% | 75% | 72% | 66% | 65% | 72% | 76% | 63% | |
| 88.9% | 92% | 85% | 82% | 89% | 92% | 89% | 92% | 97% | 92% | 92% | 85% | 94% | 85% | 98% | 92% | 93% | 89% | 88% | 89% | 76% | 76% |