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 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 92.7% | 6th 81.7% | 7th 79.3% | 8th 77.3% | 5th 83.7% | 3rd 87.3% | 18th 72.7% | 20th 68.3% | 16th 73.7% | 16th 73.7% | 12th 75.0% | 14th 74.3% | 21st 67.7% | 14th 74.3% | 2nd 90.7% | 11th 75.7% | 12th 75.0% | 9th 76.0% | 10th 76.0% | 19th 71.3% | 4th 86.0% | |
| 91.6% | 94% | 88% | 96% | 88% | 93% | 90% | 87% | 91% | 92% | 92% | 96% | 93% | 86% | 96% | 91% | 89% | 90% | 96% | 97% | 92% | 86% | |
| 75.1% | 84% | 91% | 81% | 78% | 79% | 88% | 70% | 61% | 74% | 71% | 74% | 71% | 58% | 74% | 81% | 80% | 77% | 77% | 70% | 67% | 72% | |
| 66.5% | 100% | 66% | 61% | 66% | 79% | 84% | 61% | 53% | 55% | 58% | 55% | 59% | 59% | 53% | 100% | 58% | 58% | 55% | 61% | 55% | 100% |