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 | 3rd 80.8% | 5th 80.8% | 3rd 80.8% | 1st 83.0% | 7th 79.3% | 20th 72.8% | 9th 78.0% | 17th 75.8% | 8th 78.5% | 2nd 81.8% | 14th 76.8% | 19th 73.3% | 21st 71.8% | 18th 73.8% | 9th 78.0% | 12th 77.0% | 5th 80.8% | 15th 76.5% | 12th 77.0% | 16th 76.3% | 11th 77.5% | |
| 84.2% | 89% | 86% | 100% | 100% | 97% | 85% | 96% | 93% | 93% | 90% | 86% | 90% | 56% | 80% | 84% | 82% | 75% | 72% | 87% | 71% | 56% | |
| 76.0% | 81% | 81% | 75% | 82% | 83% | 68% | 73% | 70% | 59% | 75% | 70% | 71% | 73% | 76% | 75% | 77% | 83% | 76% | 76% | 73% | 100% | |
| 66.5% | 70% | 74% | 70% | 70% | 67% | 61% | 60% | 60% | 62% | 64% | 68% | 62% | 60% | 62% | 70% | 70% | 67% | 82% | 70% | 67% | 60% | |
| 83.7% | 83% | 82% | 78% | 80% | 70% | 77% | 83% | 80% | 100% | 98% | 83% | 70% | 98% | 77% | 83% | 79% | 98% | 76% | 75% | 94% | 94% |