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 [synth]: Predict response distributions for More concerned than excited. Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude Haiku 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | |
|---|---|---|---|---|---|---|---|
| Score | 5th 56.8% | 3rd 60.4% | 1st 66.1% | 4th 58.2% | 6th 54.5% | 2nd 61.0% | |
| 61.2% | 62% | 62% | 65% | 65% | 52% | 61% | |
| 92.0% | 62% | 100% | 100% | 90% | 100% | 100% | |
| 60.5% | 71% | 60% | 71% | 60% | 44% | 57% | |
| 57.5% | 56% | 52% | 63% | 62% | 52% | 60% | |
| 37.3% | 44% | 42% | 47% | 30% | 30% | 31% | |
| 72.2% | 74% | 66% | 76% | 75% | 67% | 75% | |
| 49.2% | 17% | 67% | 66% | 19% | 65% | 61% | |
| 63.7% | 58% | 59% | 70% | 71% | 59% | 65% | |
| 43.0% | 67% | 39% | 39% | 52% | 18% | 43% | |
| 58.5% | 57% | 57% | 64% | 58% | 58% | 57% |