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 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 | 6th 81.5% | 1st 83.5% | 4th 83.0% | 12th 73.0% | 11th 74.0% | 9th 75.3% | 7th 80.0% | 7th 80.0% | 2nd 83.3% | 10th 74.3% | 2nd 83.3% | 5th 82.3% | 13th 67.0% | |
| 74.9% | 81% | 74% | 81% | 80% | 52% | 66% | 75% | 72% | 90% | 64% | 87% | 74% | 78% | |
| 87.1% | 80% | 87% | 87% | 74% | 83% | 91% | 86% | 94% | 85% | 98% | 91% | 87% | 89% | |
| 85.2% | 88% | 96% | 91% | 85% | 86% | 74% | 85% | 88% | 83% | 65% | 85% | 91% | 91% | |
| 66.7% | 77% | 77% | 73% | 53% | 75% | 70% | 74% | 66% | 75% | 70% | 70% | 77% | 10% |