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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 94.0% | 9th 84.0% | 6th 87.0% | 5th 87.3% | 8th 85.3% | 9th 84.0% | 7th 86.3% | 21st 76.8% | 20th 76.8% | 9th 84.0% | 14th 82.8% | 9th 84.0% | 18th 79.5% | 19th 78.3% | 3rd 93.0% | 4th 92.0% | 15th 82.5% | 17th 80.3% | 13th 83.3% | 16th 82.5% | 2nd 93.5% | |
| 71.4% | 100% | 66% | 72% | 75% | 81% | 66% | 62% | 58% | 55% | 65% | 63% | 72% | 57% | 61% | 100% | 100% | 66% | 67% | 57% | 57% | 100% | |
| 87.5% | 90% | 87% | 94% | 85% | 81% | 89% | 97% | 75% | 68% | 86% | 92% | 83% | 90% | 87% | 93% | 88% | 88% | 90% | 92% | 91% | 91% | |
| 87.4% | 87% | 91% | 91% | 92% | 91% | 95% | 89% | 82% | 85% | 89% | 84% | 87% | 77% | 77% | 88% | 85% | 83% | 87% | 92% | 90% | 94% | |
| 92.1% | 99% | 92% | 91% | 97% | 88% | 86% | 97% | 92% | 99% | 96% | 92% | 94% | 94% | 88% | 91% | 95% | 93% | 77% | 92% | 92% | 89% |