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% | 11th 68.3% | 15th 66.0% | 20th 62.0% | 19th 62.3% | 16th 64.7% | 4th 72.7% | 10th 68.7% | 18th 63.0% | 16th 64.7% | 14th 67.3% | 1st 75.0% | 13th 68.3% | 3rd 73.0% | - - | 11th 68.3% | 2nd 73.0% | 8th 70.0% | |
| 70.5% | 72% | 72% | 72% | 72% | 66% | 72% | 63% | 57% | 62% | 72% | 72% | 62% | 66% | 66% | 78% | 72% | 87% | 67% | 77% | 84% | ||
| 78.3% | 85% | 84% | 85% | 85% | 81% | 75% | 70% | 67% | 78% | 85% | 71% | 60% | 70% | 78% | 88% | 85% | 78% | 80% | 91% | 70% | ||
| 56.9% | 60% | 55% | 51% | 59% | 58% | 51% | 53% | 63% | 54% | 61% | 63% | 67% | 58% | 58% | 59% | 48% | 54% | 58% | 51% | 56% |