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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 7th 76.3% | 9th 74.7% | 18th 69.7% | 17th 70.0% | 15th 70.3% | 21st 61.0% | 20th 63.7% | 19th 68.3% | 14th 70.7% | 9th 74.7% | 6th 76.7% | 16th 70.3% | 4th 78.0% | 13th 72.0% | 4th 78.0% | 8th 75.3% | 11th 73.7% | 1st 94.0% | 3rd 78.7% | 12th 73.0% | 2nd 88.3% | |
| 87.6% | 95% | 86% | 78% | 78% | 83% | 74% | 82% | 80% | 80% | 98% | 95% | 95% | 98% | 77% | 95% | 87% | 83% | 94% | 98% | 92% | 92% | |
| 68.8% | 76% | 76% | 79% | 68% | 77% | 59% | 57% | 56% | 71% | 68% | 63% | 56% | 64% | 63% | 76% | 75% | 67% | 70% | 63% | 92% | ||
| 63.4% | 58% | 62% | 52% | 64% | 51% | 50% | 52% | 69% | 61% | 58% | 72% | 60% | 72% | 76% | 63% | 64% | 71% | 68% | 64% | 81% |