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 | 3rd 76.3% | 6th 74.7% | 17th 68.7% | 16th 70.0% | 15th 70.3% | 20th 62.3% | 21st 62.0% | 19th 65.7% | 12th 71.3% | 8th 72.7% | 14th 70.7% | 10th 72.0% | 5th 75.3% | 12th 71.3% | 3rd 76.3% | 10th 72.0% | 7th 73.7% | 17th 68.7% | 8th 72.7% | 2nd 83.7% | 1st 89.7% | |
| 85.1% | 95% | 80% | 78% | 78% | 76% | 74% | 82% | 80% | 80% | 98% | 80% | 95% | 98% | 83% | 98% | 80% | 86% | 82% | 80% | 92% | 92% | |
| 67.9% | 76% | 76% | 76% | 68% | 77% | 59% | 57% | 56% | 67% | 60% | 64% | 53% | 64% | 63% | 67% | 72% | 67% | 63% | 70% | 79% | 92% | |
| 64.1% | 58% | 68% | 52% | 64% | 58% | 54% | 47% | 61% | 67% | 60% | 68% | 68% | 64% | 68% | 64% | 64% | 68% | 61% | 68% | 80% | 85% |