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 Philippines. 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 | 13th 75.5% | 4th 79.0% | 11th 76.3% | 7th 77.0% | 1st 80.3% | 17th 72.5% | 2nd 79.8% | 14th 74.5% | 14th 74.5% | 5th 78.5% | 12th 75.8% | 18th 70.0% | 3rd 79.5% | 19th 69.5% | 8th 76.8% | 10th 76.8% | 20th 68.0% | 16th 73.5% | 8th 76.8% | 6th 77.3% | 21st 64.5% | |
| 52.9% | 62% | 57% | 58% | 55% | 54% | 48% | 60% | 57% | 61% | 61% | 49% | 46% | 54% | 53% | 53% | 52% | 49% | 42% | 55% | 42% | 42% | |
| 79.4% | 71% | 84% | 78% | 84% | 97% | 81% | 85% | 74% | 69% | 83% | 85% | 74% | 95% | 78% | 84% | 83% | 77% | 84% | 85% | 71% | 46% | |
| 84.6% | 85% | 90% | 86% | 86% | 93% | 76% | 89% | 85% | 83% | 85% | 84% | 76% | 84% | 71% | 85% | 88% | 73% | 84% | 89% | 96% | 88% | |
| 83.3% | 84% | 85% | 83% | 83% | 77% | 85% | 85% | 82% | 85% | 85% | 85% | 84% | 85% | 76% | 85% | 84% | 73% | 84% | 78% | 100% | 82% |