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 Pakistan. 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 | 6th 84.0% | 4th 85.7% | 6th 84.0% | 11th 82.7% | 16th 81.3% | 20th 79.0% | 14th 82.0% | 21st 78.3% | 11th 82.7% | 2nd 86.7% | 10th 83.7% | 6th 84.0% | 15th 81.7% | 2nd 86.7% | 1st 87.0% | 6th 84.0% | 17th 81.0% | 18th 80.7% | 4th 85.7% | 19th 79.3% | 13th 82.3% | |
| 88.7% | 93% | 88% | 84% | 84% | 79% | 81% | 92% | 85% | 87% | 90% | 93% | 87% | 90% | 93% | 95% | 91% | 89% | 90% | 91% | 90% | 90% | |
| 80.4% | 85% | 85% | 88% | 84% | 84% | 77% | 79% | 69% | 80% | 83% | 83% | 75% | 68% | 80% | 84% | 85% | 76% | 82% | 82% | 75% | 84% | |
| 79.9% | 74% | 84% | 80% | 80% | 81% | 79% | 75% | 81% | 81% | 87% | 75% | 90% | 87% | 87% | 82% | 76% | 78% | 70% | 84% | 73% | 73% |