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 | 1st 86.0% | 10th 81.5% | 4th 83.5% | 6th 83.0% | 17th 75.3% | 20th 74.3% | 18th 74.5% | 19th 74.3% | 13th 80.3% | 3rd 84.3% | 2nd 84.5% | 21st 70.5% | 15th 76.3% | 8th 81.8% | 11th 81.5% | 8th 81.8% | 15th 76.3% | 7th 82.3% | 4th 83.5% | 12th 80.8% | 14th 76.3% | |
| 76.6% | 80% | 81% | 74% | 81% | 75% | 52% | 66% | 78% | 74% | 84% | 90% | 58% | 75% | 87% | 82% | 80% | 80% | 80% | 78% | 79% | 75% | |
| 86.5% | 89% | 80% | 87% | 87% | 92% | 83% | 88% | 93% | 88% | 96% | 90% | 87% | 85% | 87% | 90% | 87% | 75% | 82% | 87% | 82% | 81% | |
| 84.1% | 94% | 88% | 96% | 91% | 85% | 86% | 74% | 70% | 85% | 91% | 83% | 67% | 71% | 85% | 83% | 87% | 85% | 87% | 93% | 85% | 80% | |
| 71.3% | 81% | 77% | 77% | 73% | 49% | 76% | 70% | 56% | 74% | 66% | 75% | 70% | 74% | 68% | 71% | 73% | 65% | 80% | 76% | 77% | 69% |