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 GD1 (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 | 4th 82.8% | 4th 82.8% | 6th 82.5% | 1st 84.3% | 20th 72.3% | 14th 78.0% | 16th 75.8% | 15th 77.8% | 13th 78.5% | 2nd 83.0% | 6th 82.5% | 21st 72.0% | 2nd 83.0% | 8th 81.5% | 12th 79.3% | 11th 80.3% | 17th 75.8% | 18th 75.3% | 8th 81.5% | 10th 81.0% | 19th 74.3% | |
| 61.4% | 65% | 59% | 54% | 61% | 60% | 54% | 51% | 64% | 55% | 58% | 69% | 72% | 66% | 71% | 59% | 60% | 55% | 55% | 58% | 72% | 72% | |
| 87.0% | 86% | 86% | 93% | 80% | 81% | 87% | 90% | 91% | 89% | 97% | 86% | 72% | 97% | 87% | 93% | 89% | 83% | 83% | 94% | 90% | 72% | |
| 82.5% | 87% | 90% | 86% | 99% | 84% | 82% | 78% | 82% | 86% | 86% | 84% | 61% | 83% | 79% | 76% | 87% | 72% | 80% | 89% | 82% | 80% | |
| 86.0% | 93% | 96% | 97% | 97% | 64% | 89% | 84% | 74% | 84% | 91% | 91% | 83% | 86% | 89% | 89% | 85% | 93% | 83% | 85% | 80% | 73% |