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 | 3rd 76.0% | 4th 75.3% | 8th 72.8% | 6th 74.8% | 1st 77.3% | 21st 60.8% | 16th 66.8% | 17th 66.5% | 14th 68.3% | 7th 73.5% | 11th 70.3% | 10th 71.3% | 13th 68.8% | 15th 67.8% | 2nd 76.5% | 5th 75.0% | 9th 72.3% | 19th 65.0% | 12th 70.0% | 20th 61.0% | 18th 65.5% | |
| 71.6% | 72% | 78% | 65% | 65% | 72% | 53% | 64% | 78% | 68% | 81% | 77% | 76% | 72% | 76% | 82% | 75% | 75% | 70% | 66% | 65% | 74% | |
| 84.4% | 90% | 84% | 84% | 89% | 95% | 80% | 86% | 70% | 82% | 91% | 85% | 86% | 88% | 86% | 90% | 88% | 80% | 85% | 89% | 75% | 69% | |
| 62.1% | 67% | 69% | 70% | 73% | 73% | 55% | 64% | 49% | 61% | 63% | 53% | 67% | 57% | 52% | 68% | 70% | 68% | 37% | 69% | 56% | 63% | |
| 62.9% | 75% | 70% | 72% | 72% | 69% | 55% | 53% | 69% | 62% | 59% | 66% | 56% | 58% | 57% | 66% | 67% | 66% | 68% | 56% | 48% | 56% |