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 Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | Qwen3 30b A3B Instruct 2507 | Qwen3 Next 80b A3B Instruct | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 83.7% | 5th 79.0% | 3rd 82.7% | 4th 79.3% | 13th 64.3% | 11th 71.7% | 8th 77.0% | 5th 79.0% | 7th 78.3% | 11th 71.7% | 9th 74.7% | 10th 74.3% | 1st 86.0% | |
| 82.0% | 89% | 87% | 89% | 78% | 73% | 75% | 81% | 79% | 87% | 75% | 78% | 80% | 95% | |
| 70.6% | 78% | 77% | 83% | 79% | 61% | 62% | 72% | 72% | 68% | 60% | 60% | 65% | 81% | |
| 78.5% | 84% | 73% | 76% | 81% | 59% | 78% | 78% | 86% | 80% | 80% | 86% | 78% | 82% |