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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 86.3% | 17th 71.3% | 5th 77.7% | 7th 77.3% | 21st 65.8% | 6th 77.5% | 20th 66.0% | 14th 74.5% | 9th 76.3% | 4th 78.0% | 19th 68.3% | 3rd 81.2% | 11th 76.0% | 16th 72.0% | 12th 75.3% | 15th 72.8% | 13th 74.5% | 2nd 83.0% | 10th 76.0% | 8th 76.5% | 18th 70.3% | |
| 57.6% | 100% | 48% | 52% | 57% | 59% | 53% | 55% | 63% | 51% | 46% | 26% | 62% | 58% | 100% | 66% | 54% | 51% | 57% | 44% | 49% | 59% | |
| 85.8% | 94% | 71% | 86% | 91% | 81% | 87% | 85% | 90% | 97% | 94% | 69% | 95% | 88% | 64% | 80% | 92% | 88% | 98% | 90% | 88% | 73% | |
| 69.1% | 75% | 75% | 76% | 76% | 58% | 76% | 56% | 56% | 71% | 77% | 89% | 74% | 63% | 38% | 64% | 54% | 72% | 86% | 76% | |||
| 87.4% | 76% | 91% | 97% | 85% | 65% | 94% | 68% | 89% | 86% | 95% | 89% | 94% | 95% | 86% | 91% | 91% | 87% | 91% | 94% | 93% | 79% |