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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 7th 76.0% | 8th 74.8% | 9th 74.0% | 16th 69.8% | 4th 77.8% | 18th 68.5% | 14th 70.5% | 11th 71.5% | 20th 67.5% | 15th 70.5% | 6th 76.3% | 19th 67.8% | 1st 80.5% | 13th 70.8% | 2nd 80.0% | 10th 73.0% | 17th 69.3% | 20th 67.5% | 4th 77.8% | 11th 71.5% | 3rd 78.5% | |
| 59.5% | 58% | 58% | 57% | 42% | 57% | 51% | 61% | 50% | 58% | 58% | 64% | 44% | 66% | 81% | 74% | 61% | 58% | 49% | 74% | 61% | 67% | |
| 75.8% | 72% | 81% | 75% | 72% | 77% | 83% | 74% | 77% | 67% | 72% | 91% | 72% | 77% | 62% | 91% | 75% | 77% | 77% | 72% | 65% | 82% | |
| 82.4% | 100% | 86% | 86% | 91% | 100% | 68% | 73% | 82% | 73% | 76% | 91% | 78% | 88% | 66% | 78% | 79% | 66% | 82% | 88% | 91% | 88% | |
| 74.5% | 74% | 74% | 78% | 74% | 77% | 72% | 74% | 77% | 72% | 76% | 59% | 77% | 91% | 74% | 77% | 77% | 76% | 62% | 77% | 69% | 77% |