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 | 5th 86.3% | 2nd 88.3% | 6th 85.7% | 4th 87.0% | 17th 80.3% | 9th 84.0% | 19th 78.3% | 21st 74.0% | 9th 84.0% | 7th 84.7% | 9th 84.0% | 20th 75.0% | 9th 84.0% | 14th 81.7% | 1st 88.7% | 8th 84.3% | 14th 81.7% | 13th 82.3% | 2nd 88.3% | 16th 81.3% | 18th 79.7% | |
| 87.1% | 90% | 92% | 94% | 94% | 70% | 91% | 88% | 70% | 84% | 92% | 87% | 87% | 87% | 84% | 93% | 89% | 90% | 86% | 89% | 83% | 89% | |
| 79.3% | 83% | 84% | 87% | 83% | 83% | 84% | 75% | 72% | 83% | 84% | 79% | 64% | 75% | 67% | 87% | 81% | 83% | 77% | 87% | 78% | 70% | |
| 82.7% | 86% | 89% | 76% | 84% | 88% | 77% | 72% | 80% | 85% | 78% | 86% | 74% | 90% | 94% | 86% | 83% | 72% | 84% | 89% | 83% | 80% |