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 83.5% | 13th 81.3% | 2nd 84.7% | 9th 82.3% | 18th 75.5% | 21st 74.0% | 18th 75.5% | 20th 74.8% | 14th 80.3% | 9th 82.3% | 3rd 84.5% | 16th 77.5% | 15th 79.0% | 5th 83.3% | 7th 82.8% | 6th 83.0% | 17th 76.8% | 12th 82.0% | 9th 82.3% | 8th 82.7% | 1st 88.2% | |
| 78.5% | 77% | 81% | 74% | 78% | 75% | 52% | 66% | 78% | 77% | 84% | 90% | 70% | 75% | 87% | 85% | 80% | 83% | 80% | 78% | 80% | 98% | |
| 87.3% | 89% | 80% | 87% | 87% | 90% | 83% | 91% | 95% | 85% | 94% | 90% | 98% | 87% | 91% | 91% | 88% | 71% | 84% | 84% | 82% | ||
| 85.2% | 87% | 87% | 96% | 91% | 85% | 86% | 74% | 70% | 85% | 85% | 83% | 72% | 79% | 85% | 84% | 92% | 85% | 87% | 91% | 88% | 97% | |
| 72.2% | 81% | 77% | 82% | 73% | 52% | 75% | 71% | 56% | 74% | 66% | 75% | 70% | 75% | 70% | 71% | 72% | 68% | 77% | 76% | 80% | 76% |