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 67.8% | 9th 66.5% | 1st 68.3% | 2nd 68.0% | 3rd 68.0% | 21st 57.5% | 19th 58.0% | 17th 59.3% | 13th 62.5% | 4th 67.8% | 12th 63.0% | 15th 60.3% | 14th 60.8% | 10th 64.5% | 7th 67.3% | 4th 67.8% | 18th 58.3% | 8th 66.8% | 11th 63.7% | 20th 58.0% | 16th 59.8% | |
| 61.3% | 62% | 61% | 62% | 60% | 66% | 52% | 62% | 56% | 57% | 66% | 62% | 60% | 66% | 67% | 61% | 65% | 53% | 67% | 57% | 58% | 68% | |
| 69.0% | 72% | 68% | 72% | 69% | 76% | 69% | 65% | 73% | 69% | 74% | 69% | 63% | 66% | 72% | 71% | 68% | 66% | 67% | 67% | 67% | 65% | |
| 54.3% | 58% | 59% | 60% | 64% | 63% | 47% | 51% | 46% | 51% | 64% | 50% | 50% | 44% | 50% | 60% | 66% | 48% | 57% | 60% | 48% | 45% | |
| 69.4% | 79% | 78% | 79% | 79% | 67% | 62% | 54% | 62% | 73% | 67% | 71% | 68% | 67% | 69% | 77% | 72% | 66% | 76% | 71% | 59% | 61% |