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 GD1 (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 | 5th 80.0% | 3rd 82.5% | 2nd 83.0% | 10th 75.5% | 12th 73.8% | 7th 78.0% | 6th 79.5% | 1st 84.8% | 9th 76.8% | 13th 69.8% | 11th 73.8% | 8th 77.8% | 4th 82.3% | |
| 89.1% | 86% | 100% | 100% | 97% | 85% | 96% | 92% | 90% | 86% | 82% | 80% | 83% | 81% | |
| 74.6% | 79% | 82% | 82% | 68% | 72% | 73% | 64% | 81% | 70% | 71% | 76% | 76% | 76% | |
| 66.9% | 74% | 70% | 70% | 77% | 61% | 60% | 64% | 70% | 68% | 50% | 62% | 70% | 74% | |
| 82.4% | 81% | 78% | 80% | 60% | 77% | 83% | 98% | 98% | 83% | 76% | 77% | 82% | 98% |