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 Kazakhstan. 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 | 1st 77.7% | 15th 70.3% | 3rd 75.0% | 9th 73.7% | 7th 74.0% | 17th 67.3% | 3rd 75.0% | 2nd 75.7% | 8th 74.0% | 11th 71.0% | 10th 71.3% | 19th 66.0% | 18th 66.7% | 16th 69.7% | 6th 74.7% | 11th 71.0% | 13th 70.7% | 19th 66.0% | 3rd 75.0% | 13th 70.7% | 21st 63.0% | |
| 72.9% | 83% | 69% | 65% | 65% | 76% | 59% | 83% | 85% | 83% | 78% | 69% | 74% | 74% | 78% | 78% | 69% | 69% | 64% | 76% | 67% | 67% | |
| 54.1% | 61% | 51% | 66% | 61% | 54% | 52% | 56% | 49% | 53% | 54% | 56% | 46% | 44% | 49% | 59% | 56% | 46% | 37% | 63% | 67% | 56% | |
| 87.0% | 89% | 91% | 94% | 95% | 92% | 91% | 86% | 93% | 86% | 81% | 89% | 78% | 82% | 82% | 87% | 88% | 97% | 97% | 86% | 78% | 66% |