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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 87.3% | 1st 88.3% | 5th 86.0% | 3rd 87.0% | 19th 77.7% | 19th 77.7% | 17th 78.7% | 21st 75.3% | 14th 82.0% | 10th 84.0% | 11th 83.7% | 17th 78.7% | 14th 82.0% | 11th 83.7% | 7th 85.7% | 13th 82.7% | 16th 80.0% | 5th 86.0% | 4th 86.3% | 9th 84.5% | 8th 85.0% | |
| 86.9% | 95% | 92% | 95% | 94% | 70% | 91% | 89% | 71% | 82% | 89% | 87% | 87% | 89% | 87% | 85% | 80% | 87% | 89% | 89% | 89% | ||
| 80.8% | 83% | 84% | 87% | 83% | 81% | 82% | 75% | 72% | 81% | 85% | 78% | 79% | 69% | 72% | 86% | 83% | 77% | 85% | 86% | 83% | 86% | |
| 81.3% | 84% | 89% | 76% | 84% | 82% | 60% | 72% | 83% | 83% | 78% | 86% | 70% | 88% | 92% | 86% | 85% | 76% | 84% | 84% | 86% | 80% |