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 | 4th 80.3% | 9th 76.8% | 15th 73.0% | 7th 77.3% | 17th 70.5% | 20th 65.8% | 18th 69.8% | 19th 68.0% | 12th 74.8% | 5th 80.0% | 10th 76.8% | 20th 65.8% | 11th 76.5% | 14th 73.5% | 3rd 81.3% | 8th 77.0% | 13th 74.5% | 16th 72.3% | 2nd 81.7% | 6th 78.7% | 1st 85.0% | |
| 68.1% | 73% | 68% | 60% | 69% | 67% | 54% | 65% | 64% | 71% | 78% | 77% | 60% | 78% | 70% | 75% | 69% | 66% | 66% | 73% | 65% | 63% | |
| 78.5% | 82% | 77% | 78% | 84% | 77% | 71% | 80% | 77% | 77% | 85% | 77% | 71% | 85% | 77% | 84% | 74% | 72% | 77% | 84% | 73% | 87% | |
| 69.7% | 74% | 75% | 69% | 71% | 71% | 59% | 51% | 51% | 71% | 74% | 69% | 57% | 55% | 64% | 71% | 81% | 76% | 69% | 78% | 82% | 95% | |
| 84.4% | 92% | 87% | 85% | 85% | 67% | 79% | 83% | 80% | 80% | 83% | 84% | 75% | 88% | 83% | 95% | 84% | 84% | 77% | 92% | 95% | 95% |