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 Vietnam. 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 | 1st 86.0% | 4th 76.8% | 2nd 81.5% | 9th 75.3% | 14th 74.0% | 21st 67.3% | 17th 70.8% | 15th 73.3% | 13th 74.3% | 10th 74.8% | 11th 74.5% | 18th 69.8% | 8th 75.8% | 6th 76.0% | 5th 76.5% | 7th 75.8% | 19th 69.5% | 20th 68.5% | 16th 71.0% | 11th 74.5% | 3rd 78.7% | |
| 79.7% | 91% | 79% | 77% | 77% | 77% | 62% | 70% | 82% | 90% | 86% | 82% | 86% | 90% | 91% | 79% | 83% | 74% | 72% | 72% | 77% | 77% | |
| 72.6% | 82% | 74% | 75% | 70% | 73% | 73% | 75% | 75% | 72% | 75% | 67% | 59% | 75% | 75% | 76% | 74% | 64% | 67% | 75% | 77% | ||
| 68.3% | 77% | 72% | 77% | 77% | 73% | 57% | 67% | 65% | 64% | 67% | 67% | 63% | 67% | 67% | 77% | 72% | 67% | 62% | 66% | 58% | 73% | |
| 77.0% | 94% | 82% | 97% | 77% | 73% | 77% | 71% | 71% | 71% | 71% | 82% | 71% | 71% | 71% | 74% | 74% | 73% | 73% | 71% | 86% | 86% |