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 | 17th 71.7% | 9th 73.7% | 3rd 79.0% | 2nd 80.7% | 4th 78.3% | 21st 66.7% | 1st 81.0% | 13th 73.0% | 7th 75.0% | 12th 73.3% | 19th 70.3% | 19th 70.3% | 15th 72.0% | 18th 71.3% | 9th 73.7% | 9th 73.7% | 15th 72.0% | 13th 73.0% | 5th 77.3% | 8th 74.7% | 6th 76.0% | |
| 72.8% | 64% | 66% | 76% | 76% | 75% | 72% | 90% | 76% | 76% | 72% | 71% | 76% | 71% | 78% | 64% | 64% | 69% | 64% | 76% | 76% | 76% | |
| 58.9% | 62% | 66% | 66% | 71% | 75% | 45% | 62% | 48% | 53% | 58% | 51% | 51% | 56% | 51% | 66% | 66% | 55% | 63% | 62% | 54% | 55% | |
| 90.8% | 89% | 89% | 95% | 95% | 85% | 83% | 91% | 95% | 96% | 90% | 89% | 84% | 89% | 85% | 91% | 91% | 92% | 92% | 94% | 94% | 97% |