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 Italy. 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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 12th 73.0% | 3rd 79.8% | 6th 75.5% | 18th 70.5% | 16th 71.5% | 10th 73.5% | 8th 75.0% | 14th 72.5% | 15th 71.8% | 17th 71.0% | 4th 78.5% | 19th 70.0% | 1st 80.5% | 20th 68.0% | 9th 73.8% | 1st 80.5% | 7th 75.3% | 13th 72.5% | 21st 49.3% | 5th 76.8% | 10th 73.5% | |
| 68.9% | 73% | 80% | 65% | 57% | 60% | 57% | 75% | 65% | 73% | 67% | 86% | 60% | 83% | 69% | 72% | 87% | 77% | 87% | 0% | 72% | 82% | |
| 84.3% | 71% | 91% | 90% | 83% | 78% | 96% | 86% | 81% | 76% | 75% | 83% | 75% | 91% | 73% | 87% | 90% | 96% | 88% | 83% | 87% | 90% | |
| 60.0% | 65% | 65% | 70% | 65% | 65% | 64% | 66% | 56% | 57% | 59% | 74% | 62% | 65% | 47% | 53% | 62% | 45% | 39% | 65% | 65% | 51% | |
| 80.2% | 83% | 83% | 77% | 77% | 83% | 77% | 73% | 88% | 81% | 83% | 71% | 83% | 83% | 83% | 83% | 83% | 83% | 76% | 83% | 71% |