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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 4th 83.3% | 8th 83.0% | 2nd 86.5% | 6th 83.0% | 20th 74.5% | 17th 76.5% | 21st 74.0% | 19th 74.5% | 15th 80.3% | 11th 82.3% | 4th 83.3% | 18th 75.3% | 12th 82.0% | 9th 82.7% | 1st 87.8% | 10th 82.5% | 16th 80.0% | 6th 83.0% | 13th 81.3% | 13th 81.3% | 3rd 85.5% | |
| 78.8% | 80% | 81% | 81% | 81% | 80% | 61% | 66% | 81% | 76% | 82% | 90% | 64% | 84% | 85% | 82% | 80% | 83% | 80% | 74% | 78% | 85% | |
| 87.9% | 89% | 84% | 87% | 87% | 81% | 84% | 88% | 93% | 86% | 96% | 85% | 91% | 89% | 91% | 98% | 87% | 84% | 82% | 84% | 82% | 98% | |
| 84.2% | 83% | 90% | 96% | 91% | 85% | 86% | 71% | 68% | 85% | 85% | 83% | 78% | 78% | 85% | 91% | 86% | 79% | 93% | 91% | 85% | 79% | |
| 73.4% | 81% | 77% | 82% | 73% | 52% | 75% | 71% | 56% | 74% | 66% | 75% | 68% | 77% | 70% | 80% | 77% | 74% | 77% | 76% | 80% | 80% |