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 | 5th 83.0% | 7th 82.8% | 1st 84.3% | 1st 84.3% | 19th 75.8% | 13th 78.5% | 16th 77.3% | 15th 77.5% | 14th 78.3% | 8th 82.7% | 9th 81.5% | 20th 73.3% | 4th 83.2% | 11th 80.5% | 6th 82.8% | 17th 77.0% | 18th 76.5% | 12th 78.8% | 3rd 83.3% | 21st 73.0% | 10th 81.0% | |
| 60.9% | 62% | 59% | 61% | 61% | 67% | 53% | 51% | 62% | 55% | 58% | 64% | 64% | 66% | 71% | 65% | 56% | 59% | 59% | 58% | 55% | 72% | |
| 86.9% | 93% | 86% | 93% | 80% | 81% | 87% | 90% | 92% | 89% | 97% | 86% | 76% | 97% | 87% | 90% | 83% | 86% | 83% | 94% | 72% | 83% | |
| 83.8% | 86% | 90% | 86% | 99% | 83% | 82% | 84% | 79% | 86% | 90% | 83% | 69% | 84% | 79% | 81% | 84% | 82% | 83% | 88% | 80% | 82% | |
| 87.5% | 91% | 96% | 97% | 97% | 72% | 92% | 84% | 77% | 83% | 86% | 93% | 84% | 86% | 85% | 95% | 85% | 79% | 90% | 93% | 85% | 87% |