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 84.3% | 11th 81.8% | 2nd 84.7% | 6th 83.0% | 15th 77.3% | 19th 74.3% | 17th 75.3% | 18th 74.8% | 13th 80.0% | 9th 82.8% | 3rd 84.5% | 21st 72.0% | 16th 77.3% | 5th 83.3% | 10th 82.5% | 14th 79.5% | 20th 72.5% | 8th 82.8% | 6th 83.0% | 12th 81.3% | 1st 86.7% | |
| 78.4% | 80% | 81% | 74% | 81% | 74% | 52% | 66% | 77% | 77% | 84% | 90% | 64% | 75% | 87% | 85% | 80% | 83% | 87% | 78% | 86% | 85% | |
| 86.8% | 89% | 80% | 87% | 87% | 90% | 84% | 91% | 94% | 86% | 96% | 90% | 87% | 85% | 91% | 90% | 85% | 71% | 77% | 87% | 77% | 98% | |
| 83.2% | 87% | 89% | 96% | 91% | 93% | 86% | 74% | 70% | 85% | 85% | 83% | 67% | 79% | 85% | 85% | 82% | 71% | 87% | 91% | 85% | 77% | |
| 71.5% | 81% | 77% | 82% | 73% | 52% | 75% | 70% | 58% | 72% | 66% | 75% | 70% | 70% | 70% | 70% | 71% | 65% | 80% | 76% | 77% |