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 excited than concerned. 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 | 5th 91.5% | 11th 84.0% | 9th 85.8% | 7th 86.8% | 1st 94.8% | 10th 85.5% | 8th 86.3% | 21st 76.3% | 19th 78.3% | 16th 80.5% | 12th 83.3% | 20th 77.8% | 13th 83.0% | 18th 79.3% | 2nd 93.8% | 6th 91.3% | 17th 79.8% | 3rd 93.3% | 14th 82.5% | 14th 82.5% | 4th 92.0% | |
| 73.0% | 100% | 66% | 66% | 73% | 100% | 73% | 62% | 59% | 55% | 63% | 63% | 59% | 57% | 61% | 100% | 100% | 61% | 100% | 57% | 59% | 100% | |
| 87.1% | 86% | 87% | 94% | 85% | 86% | 89% | 97% | 75% | 75% | 75% | 91% | 90% | 93% | 91% | 92% | 85% | 82% | 90% | 89% | 87% | 91% | |
| 88.1% | 87% | 91% | 92% | 92% | 96% | 95% | 89% | 82% | 84% | 88% | 87% | 84% | 87% | 77% | 89% | 86% | 85% | 89% | 92% | 90% | 88% | |
| 92.2% | 93% | 92% | 91% | 97% | 97% | 85% | 97% | 89% | 99% | 96% | 92% | 78% | 95% | 88% | 94% | 94% | 91% | 94% | 92% | 94% | 89% |