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 | 2nd 83.7% | 2nd 83.7% | 6th 81.3% | 5th 81.7% | 7th 79.3% | 21st 64.3% | 18th 70.3% | 11th 75.7% | 9th 78.0% | 8th 78.3% | 10th 77.7% | 16th 71.7% | 13th 73.7% | 12th 75.0% | 1st 84.7% | 4th 82.7% | 19th 70.0% | 17th 71.7% | 14th 73.0% | 20th 70.0% | 15th 72.0% | |
| 81.0% | 90% | 89% | 91% | 89% | 78% | 73% | 75% | 74% | 81% | 79% | 87% | 75% | 75% | 82% | 87% | 87% | 81% | 87% | 75% | 75% | 72% | |
| 70.0% | 77% | 78% | 77% | 83% | 79% | 61% | 63% | 67% | 72% | 72% | 66% | 60% | 66% | 61% | 81% | 79% | 64% | 53% | 73% | 63% | 74% | |
| 77.3% | 84% | 84% | 76% | 73% | 81% | 59% | 73% | 86% | 81% | 84% | 80% | 80% | 80% | 82% | 86% | 82% | 65% | 75% | 71% | 72% | 70% |