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 69.7% | 8th 69.3% | 3rd 72.7% | 15th 66.3% | 18th 65.0% | 19th 64.7% | 21st 60.0% | 19th 64.7% | 9th 69.0% | 11th 68.7% | 13th 67.3% | 16th 65.3% | 13th 67.3% | 11th 68.7% | 2nd 73.7% | 5th 72.0% | 1st 74.3% | 16th 65.3% | 5th 72.0% | 9th 69.0% | |
| 69.4% | 72% | 70% | 72% | 72% | 59% | 69% | 63% | 53% | 62% | 66% | 72% | 62% | 72% | 66% | 76% | 80% | 76% | 73% | 62% | 76% | 84% | |
| 79.3% | 85% | 84% | 85% | 85% | 89% | 75% | 75% | 67% | 78% | 85% | 71% | 73% | 70% | 78% | 69% | 80% | 80% | 96% | 80% | 91% | 70% | |
| 56.6% | 60% | 55% | 51% | 61% | 51% | 51% | 56% | 60% | 54% | 56% | 63% | 67% | 54% | 58% | 61% | 61% | 60% | 54% | 54% | 49% | 53% |