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 GD2 (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 | 5th 86.7% | 2nd 88.3% | 6th 86.0% | 4th 87.0% | 18th 77.7% | 17th 81.0% | 18th 77.7% | 21st 74.0% | 15th 83.3% | 8th 85.7% | 13th 83.7% | 20th 75.7% | 16th 81.3% | 13th 83.7% | 1st 89.0% | 10th 84.7% | 12th 84.0% | 8th 85.7% | 3rd 87.3% | 11th 84.3% | 6th 86.0% | |
| 87.5% | 93% | 92% | 95% | 94% | 70% | 91% | 89% | 69% | 82% | 89% | 87% | 78% | 87% | 87% | 95% | 92% | 87% | 95% | 89% | 87% | 89% | |
| 80.3% | 83% | 84% | 87% | 83% | 81% | 82% | 72% | 73% | 81% | 86% | 78% | 75% | 69% | 72% | 86% | 82% | 80% | 77% | 86% | 86% | 84% | |
| 82.6% | 84% | 89% | 76% | 84% | 82% | 70% | 72% | 80% | 87% | 82% | 86% | 74% | 88% | 92% | 86% | 80% | 85% | 85% | 87% | 80% | 85% |