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 | 2nd 87.0% | 14th 78.5% | 12th 80.0% | 15th 77.7% | 20th 70.8% | 21st 68.5% | 18th 73.8% | 19th 73.0% | 17th 76.5% | 16th 77.5% | 10th 80.5% | 7th 81.5% | 4th 83.0% | 13th 79.8% | 6th 82.2% | 8th 81.0% | 10th 80.5% | 9th 80.8% | 5th 82.5% | 3rd 84.5% | 1st 90.3% | |
| 65.7% | 64% | 59% | 52% | 58% | 59% | 44% | 47% | 62% | 54% | 57% | 67% | 80% | 72% | 77% | 65% | 62% | 68% | 68% | 64% | 100% | 100% | |
| 82.6% | 100% | 76% | 78% | 78% | 80% | 77% | 78% | 80% | 78% | 79% | 78% | 100% | 90% | 77% | 87% | 78% | 68% | 79% | 94% | 80% | 100% | |
| 87.1% | 95% | 95% | 95% | 95% | 78% | 73% | 91% | 79% | 95% | 95% | 88% | 66% | 88% | 83% | 95% | 95% | 88% | 83% | 95% | 79% | 79% | |
| 82.6% | 89% | 84% | 95% | 80% | 66% | 80% | 79% | 71% | 79% | 79% | 89% | 80% | 82% | 82% | 82% | 89% | 98% | 93% | 77% | 79% | 82% |