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% | 6th 76.8% | 7th 76.3% | 3rd 81.5% | 11th 74.0% | 20th 67.3% | 5th 78.0% | 16th 72.0% | 16th 72.0% | 14th 72.8% | 4th 78.3% | 15th 72.3% | 10th 76.0% | 21st 65.0% | 13th 73.0% | 9th 76.0% | 11th 74.0% | 7th 76.3% | 2nd 84.7% | 19th 70.0% | 16th 72.0% | |
| 79.4% | 91% | 77% | 75% | 77% | 77% | 62% | 77% | 70% | 83% | 90% | 77% | 76% | 82% | 72% | 90% | 91% | 82% | 74% | 100% | 72% | 73% | |
| 73.0% | 82% | 75% | 74% | 75% | 73% | 73% | 74% | 75% | 70% | 72% | 75% | 75% | 73% | 63% | 75% | 75% | 66% | 73% | 71% | 71% | ||
| 68.0% | 77% | 69% | 72% | 77% | 73% | 57% | 81% | 72% | 64% | 58% | 77% | 67% | 67% | 54% | 56% | 67% | 66% | 72% | 77% | 66% | 58% | |
| 78.9% | 94% | 86% | 84% | 97% | 73% | 77% | 80% | 71% | 71% | 71% | 84% | 71% | 82% | 71% | 71% | 71% | 82% | 86% | 77% | 71% | 86% |