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 | Grok 4 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 70.3% | 11th 63.0% | 8th 64.3% | 5th 66.3% | 1st 72.0% | 15th 61.0% | 11th 63.0% | 13th 62.3% | 18th 60.3% | 15th 61.0% | 6th 65.0% | 8th 64.3% | 10th 63.7% | 3rd 68.3% | 17th 60.7% | 7th 64.7% | 14th 62.3% | 19th 60.0% | 4th 67.7% | 21st 55.0% | 20th 58.0% | |
| 63.3% | 78% | 63% | 63% | 66% | 79% | 52% | 63% | 68% | 63% | 66% | 63% | 63% | 63% | 66% | 68% | 63% | 69% | 54% | 63% | 48% | 48% | |
| 50.5% | 57% | 48% | 57% | 57% | 55% | 52% | 52% | 48% | 43% | 44% | 57% | 52% | 44% | 52% | 48% | 52% | 43% | 48% | 60% | 44% | 48% | |
| 76.7% | 76% | 78% | 73% | 76% | 82% | 79% | 74% | 71% | 75% | 73% | 75% | 78% | 84% | 87% | 66% | 79% | 75% | 78% | 80% | 73% | 78% |