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 26-35. 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 81.0% | 1st 81.8% | 11th 77.0% | 9th 77.8% | 5th 78.8% | 3rd 80.3% | 5th 78.8% | 20th 72.2% | 17th 74.0% | 19th 73.5% | 10th 77.3% | 4th 80.0% | 8th 77.8% | 14th 75.8% | 13th 76.5% | 5th 78.8% | 18th 73.8% | 11th 77.0% | 14th 75.8% | 21st 71.5% | 16th 75.3% | |
| 76.7% | 76% | 79% | 75% | 72% | 75% | 75% | 82% | 77% | 75% | 81% | 75% | 78% | 80% | 81% | 76% | 78% | 75% | 80% | 74% | 69% | 78% | |
| 79.2% | 86% | 84% | 77% | 73% | 87% | 81% | 82% | 69% | 76% | 74% | 84% | 86% | 79% | 78% | 75% | 80% | 77% | 81% | 78% | 76% | 81% | |
| 68.6% | 72% | 74% | 75% | 76% | 72% | 78% | 72% | 61% | 58% | 63% | 63% | 72% | 69% | 64% | 73% | 73% | 59% | 63% | 72% | 64% | 68% | |
| 82.9% | 90% | 90% | 81% | 90% | 81% | 87% | 79% | 82% | 87% | 76% | 87% | 84% | 83% | 80% | 82% | 84% | 84% | 84% | 79% | 77% | 74% |