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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 5th 72.3% | 7th 70.3% | 9th 69.3% | 6th 72.0% | 12th 68.3% | 16th 66.0% | 21st 62.0% | 20th 62.3% | 17th 64.7% | 4th 72.7% | 11th 68.7% | 19th 63.0% | 17th 64.7% | 15th 67.3% | 1st 75.0% | 14th 68.3% | 3rd 73.0% | 9th 69.3% | 12th 68.3% | 2nd 73.0% | 8th 70.0% | |
| 70.8% | 72% | 72% | 72% | 72% | 66% | 72% | 63% | 57% | 62% | 72% | 72% | 62% | 66% | 66% | 78% | 72% | 87% | 75% | 67% | 77% | 84% | |
| 78.2% | 85% | 84% | 85% | 85% | 81% | 75% | 70% | 67% | 78% | 85% | 71% | 60% | 70% | 78% | 88% | 85% | 78% | 77% | 80% | 91% | 70% | |
| 56.8% | 60% | 55% | 51% | 59% | 58% | 51% | 53% | 63% | 54% | 61% | 63% | 67% | 58% | 58% | 59% | 48% | 54% | 56% | 58% | 51% | 56% |