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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 78.0% | 13th 70.7% | 5th 73.7% | 3rd 76.7% | 2nd 77.7% | 19th 67.3% | 10th 71.3% | 4th 75.3% | 5th 73.7% | 8th 71.7% | 10th 71.3% | 21st 64.3% | 15th 69.7% | 15th 69.7% | 8th 71.7% | 17th 68.3% | 12th 71.0% | 14th 70.0% | 7th 73.0% | 20th 66.3% | 18th 67.7% | |
| 73.6% | 83% | 69% | 65% | 70% | 83% | 64% | 71% | 87% | 83% | 78% | 69% | 71% | 78% | 78% | 74% | 70% | 69% | 69% | 76% | 71% | 67% | |
| 53.0% | 56% | 56% | 66% | 65% | 58% | 52% | 54% | 49% | 52% | 46% | 56% | 44% | 48% | 49% | 55% | 50% | 52% | 49% | 54% | 46% | 56% | |
| 87.6% | 95% | 87% | 90% | 95% | 92% | 86% | 89% | 90% | 86% | 91% | 89% | 78% | 83% | 82% | 86% | 85% | 92% | 92% | 89% | 82% | 80% |