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 GD2 (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 | 9th 71.3% | 3rd 76.7% | 17th 68.7% | 15th 70.0% | 10th 71.0% | 21st 62.3% | 20th 63.7% | 19th 64.0% | 13th 70.3% | 6th 74.7% | 12th 70.7% | 18th 67.0% | 10th 71.0% | 16th 69.3% | 5th 76.0% | 4th 76.7% | 7th 72.7% | 13th 70.3% | 7th 72.7% | 2nd 80.7% | 1st 89.7% | |
| 84.9% | 80% | 86% | 78% | 78% | 77% | 74% | 82% | 80% | 80% | 98% | 80% | 95% | 98% | 77% | 95% | 96% | 82% | 82% | 80% | 92% | 92% | |
| 67.0% | 76% | 76% | 76% | 68% | 77% | 59% | 57% | 56% | 70% | 68% | 64% | 38% | 53% | 63% | 71% | 71% | 68% | 64% | 70% | 70% | 92% | |
| 63.8% | 58% | 68% | 52% | 64% | 59% | 54% | 52% | 56% | 61% | 58% | 68% | 68% | 62% | 68% | 62% | 63% | 68% | 65% | 68% | 80% | 85% |