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 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 | 3rd 75.8% | 7th 73.5% | 4th 74.5% | 1st 78.3% | 2nd 76.0% | 20th 64.0% | 17th 68.8% | 19th 67.5% | 5th 74.0% | 8th 73.5% | 14th 70.5% | 18th 67.8% | 16th 69.5% | 9th 73.3% | 6th 73.8% | 12th 72.0% | 15th 70.3% | 10th 72.8% | 11th 72.2% | 21st 63.8% | 13th 71.0% | |
| 90.7% | 91% | 86% | 90% | 100% | 90% | 83% | 95% | 88% | 95% | 94% | 85% | 90% | 97% | 89% | 92% | 87% | 85% | 89% | 94% | 87% | 97% | |
| 67.8% | 74% | 74% | 70% | 70% | 72% | 65% | 70% | 60% | 68% | 70% | 70% | 59% | 67% | 71% | 63% | 72% | 67% | 65% | 71% | 54% | 72% | |
| 58.0% | 64% | 60% | 65% | 70% | 75% | 43% | 46% | 52% | 58% | 60% | 54% | 57% | 51% | 57% | 70% | 61% | 54% | 62% | 54% | 51% | 54% | |
| 69.7% | 74% | 74% | 73% | 73% | 67% | 65% | 64% | 70% | 75% | 70% | 73% | 65% | 63% | 76% | 70% | 68% | 75% | 75% | 70% | 63% | 61% |