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 Non-binary. 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 | 13th 70.5% | 3rd 75.3% | 11th 71.0% | 14th 70.3% | 6th 73.8% | 20th 64.8% | 16th 68.8% | 4th 75.0% | 21st 62.5% | 15th 69.2% | 7th 73.0% | 16th 68.8% | 1st 78.5% | 19th 65.0% | 9th 72.0% | 5th 74.5% | 2nd 76.3% | 10th 71.8% | 18th 68.0% | 8th 72.5% | 12th 70.8% | |
| 76.7% | 73% | 79% | 77% | 73% | 79% | 68% | 76% | 73% | 69% | 73% | 81% | 72% | 88% | 61% | 79% | 77% | 90% | 90% | 64% | 79% | 89% | |
| 70.8% | 71% | 73% | 73% | 65% | 66% | 69% | 71% | 77% | 52% | 61% | 73% | 71% | 81% | 64% | 71% | 71% | 82% | 80% | 71% | 73% | 71% | |
| 68.0% | 73% | 78% | 74% | 78% | 70% | 62% | 60% | 70% | 55% | 63% | 73% | 67% | 77% | 67% | 67% | 73% | 60% | 61% | 66% | 73% | 62% | |
| 68.7% | 65% | 71% | 60% | 65% | 80% | 60% | 68% | 80% | 74% | 80% | 65% | 65% | 68% | 68% | 71% | 77% | 73% | 56% | 71% | 65% | 61% |