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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 86.0% | 3rd 78.0% | 6th 76.8% | 2nd 79.7% | 15th 72.5% | 21st 64.5% | 4th 77.3% | 17th 72.0% | 12th 73.3% | 13th 72.8% | 15th 72.5% | 10th 75.3% | 9th 76.0% | 20th 67.3% | 7th 76.3% | 8th 76.0% | 18th 71.5% | 11th 73.5% | 4th 77.3% | 19th 70.5% | 13th 72.8% | |
| 78.6% | 91% | 77% | 79% | 70% | 72% | 62% | 82% | 70% | 82% | 90% | 77% | 88% | 82% | 72% | 90% | 91% | 82% | 73% | 86% | 70% | 64% | |
| 73.0% | 82% | 80% | 74% | 75% | 74% | 62% | 73% | 75% | 75% | 72% | 71% | 75% | 73% | 59% | 75% | 75% | 64% | 73% | 75% | 75% | 77% | |
| 69.1% | 77% | 69% | 72% | 77% | 73% | 57% | 74% | 72% | 65% | 58% | 67% | 67% | 67% | 63% | 69% | 67% | 67% | 62% | 77% | 66% | 86% | |
| 76.7% | 94% | 86% | 82% | 97% | 71% | 77% | 80% | 71% | 71% | 71% | 75% | 71% | 82% | 75% | 71% | 71% | 73% | 86% | 71% | 71% | 64% |