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 More concerned than excited. 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 | 3rd 83.8% | 9th 77.5% | 7th 80.3% | 4th 83.5% | 20th 70.5% | 18th 73.0% | 11th 77.0% | 10th 77.3% | 6th 81.8% | 5th 82.5% | 15th 76.5% | 21st 69.5% | 16th 74.0% | 17th 73.5% | 13th 76.8% | 1st 90.3% | 8th 78.5% | 13th 76.8% | 12th 77.0% | 19th 72.8% | 2nd 86.5% | |
| 67.3% | 100% | 54% | 57% | 69% | 76% | 51% | 74% | 54% | 53% | 67% | 58% | 100% | 67% | 55% | 61% | 100% | 59% | 59% | 49% | 51% | 100% | |
| 87.2% | 94% | 83% | 91% | 99% | 81% | 87% | 90% | 90% | 99% | 96% | 91% | 67% | 80% | 92% | 95% | 88% | 87% | 81% | 91% | 70% | 80% | |
| 68.4% | 68% | 76% | 76% | 76% | 55% | 60% | 55% | 71% | 75% | 73% | 63% | 35% | 62% | 56% | 71% | 78% | 75% | 80% | 76% | 79% | 77% | |
| 89.2% | 73% | 97% | 97% | 90% | 70% | 94% | 89% | 94% | 100% | 94% | 94% | 76% | 87% | 91% | 80% | 95% | 93% | 87% | 92% | 91% | 89% |