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 Turkey. 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 | 1st 91.3% | 11th 78.8% | 9th 80.0% | 13th 77.7% | 15th 76.0% | 21st 68.5% | 17th 75.0% | 20th 72.5% | 16th 76.0% | 14th 77.5% | 6th 81.8% | 18th 74.0% | 5th 82.2% | 10th 79.8% | 12th 77.8% | 7th 81.5% | 4th 82.3% | 18th 74.0% | 3rd 83.0% | 8th 81.3% | 2nd 90.3% | |
| 63.5% | 72% | 59% | 52% | 58% | 59% | 44% | 52% | 58% | 54% | 57% | 72% | 62% | 72% | 77% | 64% | 67% | 62% | 65% | 64% | 100% | ||
| 80.7% | 100% | 76% | 78% | 78% | 78% | 77% | 78% | 80% | 78% | 79% | 78% | 80% | 87% | 77% | 78% | 76% | 82% | 68% | 94% | 72% | 100% | |
| 86.9% | 95% | 95% | 95% | 95% | 78% | 73% | 91% | 81% | 95% | 95% | 88% | 75% | 88% | 83% | 87% | 88% | 85% | 84% | 95% | 79% | 79% | |
| 84.5% | 98% | 85% | 95% | 80% | 89% | 80% | 79% | 71% | 77% | 79% | 89% | 79% | 82% | 82% | 82% | 95% | 100% | 79% | 79% | 93% | 82% |