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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 79.8% | 3rd 79.0% | 10th 74.5% | 7th 77.3% | 17th 71.8% | 15th 73.5% | 1st 80.8% | 10th 74.5% | 10th 74.5% | 6th 77.5% | 13th 74.3% | 20th 70.0% | 19th 70.3% | 18th 70.5% | 5th 78.3% | 14th 74.0% | 21st 67.0% | 8th 75.3% | 9th 75.0% | 16th 72.3% | 4th 78.8% | |
| 52.8% | 62% | 57% | 51% | 55% | 50% | 52% | 60% | 55% | 61% | 61% | 53% | 52% | 52% | 53% | 51% | 52% | 40% | 49% | 55% | 41% | 46% | |
| 78.3% | 83% | 84% | 78% | 83% | 75% | 81% | 85% | 76% | 69% | 83% | 84% | 74% | 66% | 78% | 85% | 74% | 77% | 75% | 78% | 61% | 95% | |
| 82.8% | 89% | 90% | 86% | 86% | 85% | 76% | 93% | 85% | 83% | 81% | 75% | 70% | 78% | 71% | 85% | 88% | 73% | 94% | 89% | 87% | 74% | |
| 85.0% | 85% | 85% | 83% | 85% | 77% | 85% | 85% | 82% | 85% | 85% | 85% | 84% | 85% | 80% | 92% | 82% | 78% | 83% | 78% | 100% | 100% |