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 GD2 (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 89.0% | 15th 65.7% | 6th 75.7% | 5th 76.0% | 10th 71.3% | 20th 60.0% | 2nd 84.0% | 11th 69.0% | 17th 65.0% | 8th 72.7% | 13th 68.0% | 21st 56.7% | 18th 64.7% | 14th 66.7% | 9th 72.0% | 4th 78.3% | 18th 64.7% | 15th 65.7% | 12th 68.7% | 7th 74.0% | 3rd 82.3% | |
| 82.1% | 98% | 84% | 92% | 90% | 76% | 66% | 93% | 95% | 83% | 93% | 75% | 71% | 77% | 71% | 75% | 83% | 72% | 72% | 78% | 98% | 83% | |
| 63.8% | 69% | 67% | 78% | 69% | 45% | 63% | 59% | 63% | 58% | 59% | 66% | 55% | 50% | 62% | 73% | 68% | 63% | 66% | 77% | 65% | 64% | |
| 67.0% | 100% | 46% | 57% | 69% | 93% | 51% | 100% | 49% | 54% | 66% | 63% | 44% | 67% | 67% | 68% | 84% | 59% | 59% | 51% | 59% | 100% |