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 Slovakia. 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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 7th 69.7% | 9th 69.0% | 5th 71.3% | 4th 72.0% | 5th 71.3% | 15th 67.0% | 1st 73.7% | 16th 66.3% | 13th 68.0% | 16th 66.3% | 19th 62.7% | 2nd 73.0% | 11th 68.7% | 20th 61.3% | 11th 68.7% | 13th 68.0% | 8th 69.3% | 18th 64.7% | 2nd 73.0% | 10th 69.0% | |
| 68.9% | 59% | 60% | 74% | 74% | 61% | 59% | 88% | 66% | 74% | 74% | 63% | 74% | 74% | 63% | 64% | 64% | 74% | 61% | 74% | 78% | |
| 62.7% | 69% | 69% | 69% | 69% | 69% | 69% | 53% | 57% | 61% | 52% | 57% | 61% | 52% | 52% | 69% | 71% | 59% | 67% | 69% | 60% | |
| 74.3% | 81% | 78% | 71% | 73% | 84% | 73% | 80% | 76% | 69% | 73% | 68% | 84% | 80% | 69% | 73% | 69% | 75% | 66% | 76% | 69% |