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 | 2nd 66.7% | 1st 67.0% | 9th 61.7% | 10th 61.0% | 5th 63.3% | 12th 59.3% | 18th 54.7% | 17th 55.0% | 16th 56.7% | 19th 54.7% | 11th 60.7% | 3rd 66.0% | 14th 57.0% | 6th 62.3% | 8th 61.7% | 6th 62.3% | 15th 56.7% | 4th 63.7% | 21st 51.0% | 20th 52.7% | 13th 57.3% | |
| 63.0% | 73% | 74% | 59% | 59% | 72% | 69% | 53% | 53% | 59% | 56% | 72% | 72% | 59% | 66% | 71% | 68% | 62% | 72% | 53% | 48% | 53% | |
| 63.6% | 73% | 74% | 75% | 75% | 65% | 58% | 57% | 56% | 63% | 61% | 56% | 63% | 54% | 63% | 74% | 69% | 54% | 61% | 56% | 63% | 66% | |
| 52.1% | 54% | 53% | 51% | 49% | 53% | 51% | 54% | 56% | 48% | 47% | 54% | 63% | 58% | 58% | 40% | 50% | 54% | 58% | 44% | 47% | 53% |