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 Indonesia. 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 | 2nd 77.5% | 3rd 74.8% | 7th 72.8% | 3rd 74.8% | 6th 73.3% | 21st 61.0% | 19th 63.7% | 17th 65.8% | 14th 67.3% | 8th 72.5% | 9th 72.0% | 16th 65.8% | 18th 65.5% | 13th 67.5% | 1st 78.5% | 5th 73.3% | 11th 68.3% | 15th 66.3% | 12th 67.8% | 20th 63.3% | 10th 70.8% | |
| 69.8% | 77% | 76% | 65% | 65% | 72% | 53% | 64% | 76% | 62% | 78% | 75% | 70% | 68% | 76% | 75% | 76% | 58% | 75% | 63% | 66% | 76% | |
| 84.5% | 91% | 84% | 84% | 89% | 86% | 80% | 86% | 70% | 82% | 90% | 89% | 86% | 86% | 86% | 92% | 86% | 80% | 79% | 84% | 79% | 85% | |
| 61.9% | 67% | 69% | 70% | 73% | 72% | 56% | 52% | 54% | 63% | 63% | 58% | 51% | 51% | 52% | 73% | 66% | 68% | 43% | 69% | 60% | 69% | |
| 62.3% | 75% | 70% | 72% | 72% | 63% | 55% | 53% | 63% | 62% | 59% | 66% | 56% | 57% | 56% | 74% | 65% | 67% | 68% | 55% | 48% | 53% |