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 Turkey. 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 | 4th 72.3% | 7th 70.3% | 9th 69.3% | 6th 72.0% | 20th 61.0% | 14th 67.0% | 19th 63.0% | 21st 60.0% | 18th 63.7% | 8th 70.0% | 14th 67.0% | 4th 72.3% | 17th 65.3% | 13th 67.3% | 2nd 77.0% | 9th 69.3% | 1st 78.0% | 3rd 75.7% | 14th 67.0% | 9th 69.3% | 12th 69.0% | |
| 70.4% | 72% | 72% | 72% | 72% | 48% | 75% | 63% | 56% | 62% | 72% | 72% | 72% | 72% | 66% | 84% | 69% | 83% | 75% | 62% | 76% | 84% | |
| 80.2% | 85% | 84% | 85% | 85% | 82% | 75% | 70% | 66% | 78% | 82% | 75% | 78% | 70% | 78% | 85% | 86% | 91% | 91% | 85% | 83% | 70% | |
| 56.0% | 60% | 55% | 51% | 59% | 53% | 51% | 56% | 58% | 51% | 56% | 54% | 67% | 54% | 58% | 62% | 53% | 60% | 61% | 54% | 49% | 53% |