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 | 2nd 85.5% | 9th 82.0% | 2nd 85.5% | 4th 84.3% | 17th 76.5% | 18th 76.3% | 20th 74.3% | 19th 75.5% | 14th 79.3% | 8th 82.3% | 5th 83.3% | 21st 69.5% | 15th 78.5% | 7th 82.7% | 16th 78.5% | 11th 80.0% | 11th 80.0% | 1st 86.0% | 6th 82.8% | 13th 79.5% | 10th 80.3% | |
| 78.7% | 80% | 81% | 77% | 81% | 74% | 61% | 62% | 80% | 72% | 72% | 90% | 50% | 75% | 85% | 78% | 76% | 98% | 98% | 80% | 85% | 98% | |
| 85.4% | 89% | 80% | 87% | 87% | 87% | 83% | 91% | 94% | 86% | 96% | 85% | 91% | 87% | 91% | 85% | 90% | 79% | 82% | 84% | 77% | 62% | |
| 83.3% | 91% | 90% | 96% | 91% | 87% | 86% | 74% | 70% | 85% | 91% | 83% | 67% | 79% | 85% | 81% | 83% | 71% | 85% | 91% | 83% | 81% | |
| 72.6% | 82% | 77% | 82% | 78% | 58% | 75% | 70% | 58% | 74% | 70% | 75% | 70% | 73% | 70% | 70% | 71% | 72% | 79% | 76% | 73% |