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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 77.5% | 4th 74.8% | 8th 72.8% | 4th 74.8% | 2nd 77.3% | 21st 57.5% | 18th 64.0% | 19th 64.0% | 9th 71.0% | 7th 73.0% | 10th 70.3% | 14th 68.3% | 12th 69.5% | 13th 68.5% | 3rd 75.5% | 6th 74.3% | 16th 66.0% | 17th 64.3% | 15th 67.0% | 20th 63.5% | 11th 69.5% | |
| 71.7% | 77% | 76% | 65% | 65% | 75% | 52% | 63% | 76% | 68% | 78% | 75% | 80% | 76% | 76% | 80% | 75% | 68% | 70% | 66% | 66% | 78% | |
| 84.2% | 90% | 84% | 84% | 89% | 89% | 80% | 86% | 70% | 84% | 87% | 86% | 86% | 88% | 86% | 84% | 87% | 83% | 80% | 91% | 79% | 75% | |
| 59.9% | 67% | 69% | 70% | 73% | 73% | 43% | 54% | 47% | 70% | 63% | 58% | 51% | 57% | 52% | 72% | 66% | 47% | 39% | 55% | 60% | 71% | |
| 63.0% | 76% | 70% | 72% | 72% | 72% | 55% | 53% | 63% | 62% | 64% | 62% | 56% | 57% | 60% | 66% | 69% | 66% | 68% | 56% | 49% | 54% |