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 | 6th 78.8% | 5th 79.8% | 3rd 82.5% | 2nd 83.0% | 15th 73.0% | 14th 73.8% | 8th 78.0% | 11th 75.5% | 4th 82.0% | 1st 83.2% | 12th 75.3% | 13th 74.8% | 18th 71.8% | 16th 72.8% | 8th 78.0% | 7th 78.5% | 19th 69.5% | 16th 72.8% | 10th 77.5% | 21st 66.5% | 20th 67.0% | |
| 82.9% | 89% | 86% | 100% | 100% | 89% | 85% | 96% | 93% | 93% | 90% | 80% | 90% | 56% | 80% | 79% | 87% | 75% | 75% | 87% | 56% | 55% | |
| 74.4% | 73% | 78% | 82% | 82% | 68% | 72% | 73% | 73% | 70% | 75% | 70% | 77% | 73% | 72% | 83% | 76% | 75% | 77% | 76% | 77% | 60% | |
| 64.4% | 70% | 73% | 70% | 70% | 67% | 61% | 60% | 60% | 65% | 70% | 68% | 62% | 60% | 62% | 68% | 64% | 53% | 63% | 70% | 58% | 59% | |
| 81.9% | 83% | 82% | 78% | 80% | 68% | 77% | 83% | 76% | 100% | 98% | 83% | 70% | 98% | 77% | 82% | 87% | 75% | 76% | 77% | 75% | 94% |