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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 91.5% | 13th 83.3% | 8th 84.3% | 3rd 87.0% | 4th 86.0% | 10th 83.8% | 5th 85.5% | 2nd 87.3% | 21st 76.5% | 20th 78.8% | 19th 79.5% | 13th 83.3% | 6th 84.8% | 11th 83.5% | 11th 83.5% | 17th 80.5% | 16th 82.8% | 18th 80.3% | 15th 83.0% | 8th 84.3% | 7th 84.5% | |
| 63.6% | 100% | 57% | 66% | 72% | 76% | 66% | 70% | 62% | 57% | 55% | 41% | 61% | 63% | 72% | 59% | 61% | 60% | 57% | 63% | 61% | 57% | |
| 87.8% | 83% | 95% | 88% | 94% | 81% | 89% | 92% | 97% | 75% | 76% | 87% | 85% | 91% | 90% | 92% | 91% | 91% | 92% | 76% | 92% | 87% | |
| 89.6% | 86% | 93% | 91% | 91% | 92% | 95% | 90% | 93% | 82% | 85% | 96% | 92% | 91% | 84% | 87% | 77% | 87% | 84% | 98% | 92% | 95% | |
| 93.0% | 97% | 88% | 92% | 91% | 95% | 85% | 90% | 97% | 92% | 99% | 94% | 95% | 94% | 88% | 96% | 93% | 93% | 88% | 95% | 92% | 99% |