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 76.0% | 12th 70.7% | 6th 73.7% | 6th 73.7% | 4th 74.7% | 21st 66.3% | 2nd 75.3% | 5th 74.3% | 2nd 75.3% | 18th 69.3% | 15th 70.0% | 20th 67.0% | 14th 70.3% | 16th 69.7% | 19th 68.7% | 10th 72.3% | 8th 73.3% | 11th 71.7% | 9th 73.0% | 16th 69.7% | 12th 70.7% | |
| 73.1% | 83% | 69% | 65% | 61% | 74% | 61% | 83% | 85% | 83% | 78% | 69% | 71% | 78% | 78% | 70% | 75% | 64% | 71% | 76% | 74% | 67% | |
| 53.9% | 56% | 56% | 66% | 65% | 58% | 52% | 57% | 49% | 53% | 49% | 56% | 46% | 44% | 49% | 51% | 54% | 62% | 55% | 54% | 43% | 56% | |
| 88.1% | 89% | 87% | 90% | 95% | 92% | 86% | 86% | 89% | 90% | 81% | 85% | 84% | 89% | 82% | 85% | 88% | 94% | 89% | 89% | 92% | 89% |