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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 13th 80.0% | 3rd 84.5% | 6th 82.8% | 4th 83.5% | 12th 80.3% | 19th 75.0% | 2nd 84.8% | 16th 77.5% | 18th 77.3% | 14th 79.0% | 1st 86.5% | 10th 82.3% | 8th 82.5% | 20th 74.8% | 5th 83.3% | 9th 82.5% | 21st 73.8% | 16th 77.5% | 15th 78.8% | 6th 82.8% | 10th 82.3% | |
| 62.1% | 59% | 64% | 59% | 58% | 67% | 54% | 64% | 51% | 63% | 58% | 72% | 59% | 64% | 67% | 67% | 71% | 60% | 59% | 59% | 58% | 72% | |
| 88.8% | 83% | 96% | 86% | 93% | 95% | 78% | 97% | 90% | 91% | 89% | 97% | 93% | 90% | 76% | 97% | 90% | 68% | 83% | 87% | 94% | 91% | |
| 84.4% | 85% | 86% | 90% | 86% | 87% | 79% | 87% | 85% | 82% | 85% | 94% | 86% | 83% | 73% | 83% | 90% | 80% | 78% | 86% | 86% | 81% | |
| 86.9% | 93% | 92% | 96% | 97% | 72% | 89% | 91% | 84% | 73% | 84% | 83% | 91% | 93% | 83% | 86% | 79% | 87% | 90% | 83% | 93% | 85% |