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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 79.8% | 9th 76.8% | 10th 76.8% | 6th 79.3% | 17th 68.8% | 20th 65.8% | 13th 74.3% | 16th 69.0% | 15th 73.5% | 7th 78.5% | 11th 75.3% | 21st 65.0% | 3rd 79.8% | 14th 74.0% | 12th 74.8% | 8th 77.3% | 18th 68.5% | 19th 67.3% | 2nd 82.5% | 1st 82.8% | 5th 79.7% | |
| 67.6% | 71% | 68% | 60% | 66% | 67% | 54% | 58% | 69% | 66% | 72% | 77% | 60% | 83% | 77% | 71% | 72% | 66% | 60% | 75% | 64% | 63% | |
| 77.6% | 78% | 77% | 84% | 84% | 77% | 71% | 80% | 77% | 77% | 85% | 78% | 72% | 85% | 77% | 74% | 78% | 70% | 66% | 85% | 77% | 77% | |
| 70.0% | 74% | 74% | 78% | 82% | 72% | 59% | 76% | 55% | 71% | 74% | 62% | 54% | 59% | 59% | 71% | 75% | 56% | 62% | 78% | 95% | 84% | |
| 83.7% | 96% | 88% | 85% | 85% | 59% | 79% | 83% | 75% | 80% | 83% | 84% | 74% | 92% | 83% | 83% | 84% | 82% | 81% | 92% | 95% | 95% |