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 46-55. 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 | 10th 76.8% | 1st 83.0% | 12th 76.5% | 16th 74.8% | 2nd 81.5% | 13th 76.0% | 10th 76.8% | 20th 71.5% | 19th 72.2% | 21st 71.5% | 9th 77.8% | 7th 78.5% | 18th 74.0% | 6th 78.8% | 13th 76.0% | 3rd 80.5% | 5th 79.0% | 8th 78.0% | 4th 79.8% | 17th 74.3% | 15th 75.0% | |
| 73.8% | 74% | 78% | 68% | 64% | 79% | 68% | 80% | 73% | 69% | 68% | 75% | 81% | 75% | 87% | 59% | 73% | 78% | 83% | 74% | 70% | 74% | |
| 71.7% | 71% | 75% | 74% | 70% | 77% | 75% | 69% | 64% | 69% | 61% | 82% | 70% | 78% | 73% | 68% | 70% | 75% | 67% | 75% | 73% | 69% | |
| 70.6% | 72% | 89% | 74% | 75% | 80% | 69% | 70% | 60% | 67% | 69% | 62% | 72% | 54% | 62% | 83% | 82% | 73% | 65% | 74% | 63% | 68% | |
| 91.0% | 90% | 90% | 90% | 90% | 90% | 92% | 88% | 89% | 84% | 88% | 92% | 91% | 89% | 93% | 94% | 97% | 90% | 97% | 96% | 91% | 89% |