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 | 1st 92.8% | 11th 84.0% | 7th 85.5% | 5th 87.3% | 4th 87.8% | 7th 85.5% | 6th 86.3% | 19th 76.5% | 18th 77.8% | 9th 84.0% | 15th 82.5% | 21st 72.8% | 9th 84.0% | 19th 76.5% | 12th 83.5% | 2nd 91.8% | 17th 81.5% | 16th 82.0% | 12th 83.5% | 14th 82.8% | 3rd 91.5% | |
| 69.3% | 100% | 66% | 66% | 75% | 88% | 73% | 62% | 58% | 55% | 66% | 63% | 72% | 59% | 61% | 57% | 100% | 60% | 59% | 57% | 59% | 100% | |
| 87.5% | 88% | 87% | 94% | 85% | 79% | 89% | 97% | 75% | 72% | 85% | 91% | 92% | 92% | 80% | 91% | 86% | 89% | 92% | 92% | 90% | 91% | |
| 85.3% | 85% | 91% | 91% | 92% | 91% | 95% | 89% | 82% | 85% | 92% | 84% | 43% | 86% | 77% | 89% | 85% | 84% | 84% | 93% | 90% | 83% | |
| 93.0% | 98% | 92% | 91% | 97% | 93% | 85% | 97% | 91% | 99% | 93% | 92% | 84% | 99% | 88% | 97% | 96% | 93% | 93% | 92% | 92% | 92% |