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 Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | Qwen3 30b A3B Instruct 2507 | Qwen3 Next 80b A3B Instruct | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 10th 74.0% | 3rd 78.0% | 1st 80.7% | 4th 77.7% | 13th 68.0% | 7th 74.7% | 5th 76.7% | 8th 74.7% | 12th 71.3% | 6th 75.0% | 11th 72.0% | 2nd 78.7% | 8th 74.7% | |
| 73.8% | 66% | 76% | 76% | 76% | 76% | 71% | 76% | 76% | 64% | 76% | 76% | 76% | 74% | |
| 61.5% | 66% | 66% | 71% | 65% | 45% | 62% | 61% | 58% | 61% | 61% | 51% | 66% | 66% | |
| 90.0% | 90% | 92% | 95% | 92% | 83% | 91% | 93% | 90% | 89% | 88% | 89% | 94% | 84% |