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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 77.3% | 4th 76.0% | 6th 74.5% | 1st 78.3% | 3rd 76.8% | 20th 67.3% | 19th 68.5% | 21st 67.0% | 13th 70.5% | 7th 73.5% | 11th 71.7% | 14th 70.3% | 16th 69.2% | 8th 73.3% | 5th 75.5% | 10th 72.0% | 18th 68.8% | 12th 70.8% | 9th 72.7% | 17th 69.0% | 15th 69.5% | |
| 90.9% | 94% | 86% | 90% | 100% | 90% | 88% | 94% | 88% | 97% | 94% | 85% | 90% | 96% | 89% | 91% | 89% | 87% | 87% | 94% | 90% | 89% | |
| 68.2% | 74% | 74% | 70% | 70% | 72% | 65% | 70% | 63% | 68% | 70% | 70% | 67% | 67% | 71% | 70% | 68% | 63% | 74% | 67% | 63% | 56% | |
| 59.4% | 64% | 70% | 65% | 70% | 75% | 51% | 46% | 52% | 47% | 60% | 57% | 57% | 47% | 57% | 68% | 63% | 57% | 47% | 65% | 58% | 72% | |
| 69.6% | 77% | 74% | 73% | 73% | 70% | 65% | 64% | 65% | 70% | 70% | 75% | 67% | 67% | 76% | 73% | 68% | 68% | 75% | 65% | 65% | 61% |