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 | 5th 64.7% | 11th 63.0% | 6th 64.3% | 4th 65.3% | 1st 74.0% | 14th 61.0% | 11th 63.0% | 3rd 67.7% | 15th 60.3% | 16th 60.0% | 10th 63.3% | 6th 64.3% | 8th 63.7% | 2nd 68.3% | 18th 59.0% | 9th 63.3% | 17th 59.3% | 19th 58.0% | 13th 61.5% | 21st 53.0% | 20th 58.0% | |
| 63.1% | 68% | 63% | 63% | 63% | 87% | 52% | 63% | 68% | 63% | 63% | 63% | 63% | 63% | 66% | 63% | 63% | 67% | 64% | 63% | 49% | 48% | |
| 50.0% | 57% | 48% | 57% | 57% | 57% | 52% | 52% | 48% | 43% | 44% | 52% | 52% | 44% | 52% | 41% | 55% | 40% | 42% | 60% | 48% | 48% | |
| 75.5% | 69% | 78% | 73% | 76% | 78% | 79% | 74% | 87% | 75% | 73% | 75% | 78% | 84% | 87% | 73% | 72% | 71% | 68% | 62% | 78% |