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 | 1st 82.0% | 2nd 81.8% | 5th 79.3% | 11th 77.8% | 4th 79.3% | 5th 79.3% | 5th 79.3% | 20th 71.3% | 19th 73.8% | 12th 76.8% | 9th 78.3% | 10th 77.8% | 14th 75.5% | 18th 74.8% | 8th 79.0% | 3rd 79.5% | 14th 75.5% | 16th 75.3% | 13th 76.0% | 21st 68.8% | 17th 75.0% | |
| 76.5% | 76% | 79% | 75% | 72% | 75% | 75% | 82% | 77% | 75% | 84% | 76% | 78% | 76% | 83% | 77% | 78% | 75% | 77% | 76% | 64% | 77% | |
| 78.3% | 87% | 84% | 77% | 73% | 87% | 77% | 85% | 69% | 75% | 77% | 84% | 83% | 78% | 78% | 77% | 79% | 77% | 73% | 78% | 72% | 75% | |
| 68.9% | 74% | 74% | 75% | 76% | 74% | 78% | 71% | 56% | 58% | 63% | 63% | 72% | 66% | 58% | 80% | 76% | 66% | 61% | 71% | 62% | 73% | |
| 84.0% | 91% | 90% | 90% | 90% | 81% | 87% | 79% | 83% | 87% | 83% | 90% | 78% | 82% | 80% | 82% | 85% | 84% | 90% | 79% | 77% | 75% |