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 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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 5th 75.3% | 10th 72.8% | 18th 66.8% | 12th 72.2% | 4th 76.5% | 16th 70.0% | 13th 71.5% | 21st 65.3% | 7th 73.8% | 14th 71.3% | 3rd 80.5% | 17th 69.0% | 8th 73.5% | 9th 73.0% | 2nd 82.0% | 6th 74.8% | 19th 66.5% | 20th 65.5% | 11th 72.3% | 14th 71.3% | 1st 85.5% | |
| 57.6% | 64% | 57% | 42% | 50% | 57% | 51% | 50% | 58% | 58% | 58% | 66% | 68% | 67% | 61% | 69% | 56% | 55% | 42% | 52% | 55% | 74% | |
| 75.1% | 72% | 75% | 72% | 77% | 72% | 83% | 77% | 58% | 72% | 72% | 77% | 65% | 72% | 75% | 91% | 84% | 66% | 77% | 77% | 72% | 91% | |
| 81.0% | 91% | 81% | 91% | 88% | 100% | 74% | 82% | 73% | 88% | 78% | 88% | 66% | 78% | 79% | 77% | 85% | 68% | 66% | 91% | 81% | 77% | |
| 77.5% | 74% | 78% | 62% | 74% | 77% | 72% | 77% | 72% | 77% | 77% | 91% | 77% | 77% | 77% | 91% | 74% | 77% | 77% | 69% | 77% | 100% |