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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 8th 73.8% | 10th 72.2% | 15th 69.8% | 10th 72.2% | 6th 77.8% | 17th 68.0% | 12th 72.0% | 21st 64.0% | 14th 71.5% | 18th 67.8% | 2nd 80.5% | 20th 66.3% | 16th 69.5% | 12th 72.0% | 1st 84.8% | 5th 79.3% | 7th 74.5% | 19th 66.8% | 9th 72.8% | 4th 79.5% | 3rd 79.8% | |
| 57.0% | 58% | 57% | 42% | 50% | 57% | 51% | 50% | 58% | 61% | 44% | 66% | 67% | 67% | 61% | 64% | 52% | 55% | 35% | 61% | 68% | 74% | |
| 75.8% | 72% | 75% | 72% | 77% | 77% | 75% | 77% | 58% | 72% | 72% | 77% | 62% | 81% | 75% | 91% | 77% | 91% | 77% | 65% | 77% | 91% | |
| 81.0% | 91% | 79% | 91% | 88% | 100% | 74% | 84% | 73% | 76% | 78% | 88% | 66% | 53% | 78% | 93% | 93% | 78% | 78% | 91% | 73% | 77% | |
| 78.4% | 74% | 78% | 74% | 74% | 77% | 72% | 77% | 67% | 77% | 77% | 91% | 70% | 77% | 74% | 91% | 95% | 74% | 77% | 74% | 100% | 77% |