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 South Africa. 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 | 3rd 82.0% | 7th 76.8% | 7th 76.8% | 5th 77.0% | 16th 71.5% | 20th 67.0% | 15th 71.8% | 21st 66.8% | 13th 73.3% | 2nd 82.3% | 11th 75.0% | 14th 73.0% | 1st 83.5% | 18th 71.0% | 12th 74.8% | 10th 75.5% | 17th 71.5% | 19th 70.3% | 4th 81.5% | 6th 76.8% | 9th 75.7% | |
| 68.5% | 69% | 69% | 60% | 69% | 68% | 54% | 65% | 63% | 66% | 78% | 75% | 60% | 83% | 70% | 75% | 69% | 70% | 60% | 75% | 64% | 77% | |
| 78.9% | 85% | 78% | 84% | 84% | 77% | 76% | 80% | 72% | 76% | 85% | 82% | 80% | 100% | 77% | 77% | 76% | 71% | 68% | 85% | 66% | 77% | |
| 67.7% | 74% | 74% | 78% | 71% | 74% | 59% | 64% | 52% | 71% | 74% | 59% | 57% | 59% | 59% | 62% | 74% | 62% | 69% | 74% | 82% | 73% | |
| 85.1% | 100% | 86% | 85% | 84% | 67% | 79% | 78% | 80% | 80% | 92% | 84% | 95% | 92% | 78% | 85% | 83% | 83% | 84% | 92% | 95% |