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 93.5% | 10th 84.0% | 8th 85.5% | 5th 87.8% | 6th 87.5% | 9th 85.3% | 7th 86.3% | 21st 76.3% | 20th 78.3% | 18th 80.3% | 11th 83.3% | 16th 81.8% | 13th 82.8% | 19th 78.8% | 2nd 93.0% | 4th 91.0% | 17th 81.3% | 14th 82.5% | 11th 83.3% | 15th 82.3% | 3rd 92.0% | |
| 71.2% | 100% | 66% | 66% | 75% | 83% | 73% | 62% | 58% | 59% | 61% | 63% | 72% | 58% | 61% | 100% | 100% | 56% | 67% | 57% | 59% | 100% | |
| 86.8% | 87% | 87% | 94% | 85% | 82% | 89% | 97% | 74% | 72% | 78% | 92% | 90% | 90% | 91% | 91% | 80% | 81% | 90% | 92% | 90% | 91% | |
| 88.1% | 89% | 91% | 91% | 92% | 96% | 94% | 89% | 82% | 85% | 90% | 86% | 77% | 85% | 80% | 90% | 88% | 96% | 84% | 92% | 89% | 85% | |
| 92.1% | 98% | 92% | 91% | 99% | 89% | 85% | 97% | 91% | 97% | 92% | 92% | 88% | 98% | 83% | 91% | 96% | 92% | 89% | 92% | 91% | 92% |