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 | 1st 83.7% | 1st 83.7% | 5th 80.3% | 4th 82.7% | 8th 77.3% | 21st 68.0% | 17th 72.3% | 10th 75.7% | 11th 74.3% | 7th 78.3% | 9th 76.3% | 18th 71.7% | 13th 74.0% | 15th 73.3% | 1st 83.7% | 6th 80.0% | 20th 68.3% | 19th 71.7% | 14th 74.0% | 12th 74.3% | 16th 73.0% | |
| 80.7% | 90% | 89% | 91% | 89% | 77% | 73% | 75% | 80% | 81% | 79% | 81% | 75% | 77% | 78% | 90% | 81% | 76% | 84% | 75% | 87% | 66% | |
| 69.3% | 77% | 78% | 77% | 83% | 79% | 61% | 63% | 61% | 68% | 70% | 68% | 60% | 66% | 60% | 77% | 78% | 64% | 57% | 73% | 64% | 72% | |
| 78.1% | 84% | 84% | 73% | 76% | 76% | 70% | 79% | 86% | 74% | 86% | 80% | 80% | 79% | 82% | 84% | 81% | 65% | 74% | 74% | 72% | 81% |