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 Egypt. 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 | 2nd 73.7% | 4th 71.3% | 8th 70.0% | 13th 67.3% | 7th 70.3% | 21st 59.0% | 20th 60.3% | 5th 70.3% | 11th 68.0% | 11th 68.0% | 10th 68.3% | 9th 69.0% | 15th 65.0% | 5th 70.3% | 2nd 73.7% | 1st 75.0% | 19th 61.3% | 15th 65.0% | 14th 65.7% | 17th 64.7% | 18th 63.0% | |
| 72.0% | 75% | 76% | 77% | 77% | 77% | 69% | 64% | 78% | 78% | 68% | 78% | 69% | 69% | 78% | 77% | 73% | 61% | 68% | 69% | 66% | 66% | |
| 42.2% | 49% | 50% | 49% | 50% | 40% | 30% | 33% | 38% | 36% | 46% | 36% | 51% | 32% | 38% | 54% | 56% | 39% | 30% | 38% | 44% | 48% | |
| 88.5% | 97% | 88% | 84% | 75% | 94% | 78% | 84% | 95% | 90% | 90% | 91% | 87% | 94% | 95% | 90% | 96% | 84% | 97% | 90% | 84% | 75% |