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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 85.0% | 7th 73.3% | 10th 71.5% | 3rd 77.0% | 18th 65.8% | 9th 72.5% | 8th 72.8% | 5th 74.5% | 16th 67.5% | 20th 64.8% | 11th 71.3% | 12th 70.0% | 19th 65.3% | 6th 74.3% | 2nd 80.0% | 4th 76.3% | 14th 69.3% | 15th 67.8% | 12th 70.0% | 21st 56.5% | 17th 66.0% | |
| 67.5% | 100% | 56% | 57% | 68% | 82% | 60% | 62% | 64% | 51% | 63% | 58% | 63% | 62% | 71% | 100% | 71% | 59% | 55% | 57% | 59% | 100% | |
| 82.8% | 95% | 93% | 82% | 81% | 64% | 84% | 91% | 89% | 88% | 80% | 88% | 88% | 83% | 87% | 81% | 86% | 88% | 78% | 88% | 67% | 58% | |
| 56.7% | 62% | 61% | 67% | 76% | 58% | 59% | 55% | 60% | 54% | 50% | 52% | 42% | 49% | 52% | 70% | 71% | 52% | 49% | 53% | 52% | 46% | |
| 77.0% | 83% | 83% | 80% | 83% | 59% | 87% | 83% | 85% | 77% | 66% | 87% | 87% | 67% | 87% | 69% | 77% | 78% | 89% | 82% | 48% | 60% |