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 | 7th 62.2% | 3rd 63.5% | 3rd 63.5% | 10th 62.0% | 6th 62.8% | 21st 55.8% | 12th 61.3% | 20th 56.0% | 3rd 63.5% | 15th 60.0% | 2nd 65.0% | 18th 59.3% | 15th 60.0% | 1st 66.8% | 13th 61.0% | 7th 62.2% | 17th 59.5% | 7th 62.2% | 11th 61.8% | 14th 60.3% | 19th 58.5% | |
| 48.5% | 51% | 49% | 48% | 42% | 51% | 44% | 52% | 47% | 55% | 44% | 49% | 46% | 55% | 49% | 46% | 47% | 49% | 54% | 55% | 43% | 42% | |
| 66.3% | 68% | 66% | 70% | 70% | 67% | 61% | 69% | 56% | 66% | 61% | 77% | 61% | 71% | 77% | 63% | 69% | 65% | 61% | 71% | 67% | 57% | |
| 70.2% | 73% | 78% | 75% | 75% | 70% | 62% | 69% | 67% | 72% | 72% | 72% | 72% | 60% | 72% | 75% | 73% | 62% | 72% | 67% | 64% | 72% | |
| 60.1% | 57% | 61% | 61% | 61% | 63% | 56% | 55% | 54% | 61% | 63% | 62% | 58% | 54% | 69% | 60% | 60% | 62% | 62% | 54% | 67% | 63% |