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 concerned than excited. 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 84.5% | 19th 66.8% | 10th 77.0% | 9th 77.3% | 15th 72.3% | 13th 74.3% | 20th 66.5% | 2nd 83.8% | 7th 78.0% | 4th 81.3% | 18th 68.5% | 3rd 83.0% | 5th 78.8% | 15th 72.3% | 6th 78.5% | 14th 73.3% | 21st 64.5% | 11th 76.3% | 12th 75.8% | 8th 77.5% | 17th 70.2% | |
| 60.2% | 100% | 32% | 52% | 57% | 100% | 51% | 55% | 100% | 54% | 53% | 32% | 65% | 59% | 100% | 74% | 55% | 15% | 59% | 44% | 49% | 59% | |
| 85.3% | 92% | 71% | 83% | 91% | 81% | 92% | 85% | 91% | 95% | 97% | 71% | 98% | 91% | 67% | 80% | 93% | 84% | 74% | 93% | 91% | 71% | |
| 67.7% | 64% | 71% | 76% | 76% | 56% | 60% | 56% | 55% | 72% | 75% | 89% | 74% | 72% | 35% | 62% | 54% | 72% | 78% | 77% | 78% | 69% | |
| 87.8% | 82% | 93% | 97% | 85% | 52% | 94% | 70% | 89% | 91% | 100% | 82% | 95% | 93% | 87% | 98% | 91% | 87% | 94% | 89% | 92% | 82% |