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 Morocco. 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 | 2nd 72.3% | 6th 69.0% | 7th 68.8% | 11th 65.0% | 1st 74.5% | 21st 56.0% | 17th 58.7% | 16th 60.3% | 15th 61.5% | 8th 68.5% | 9th 67.5% | 20th 56.8% | 14th 63.0% | 13th 63.7% | 4th 70.5% | 5th 70.0% | 10th 65.3% | 3rd 71.0% | 18th 58.0% | 19th 57.3% | 12th 63.8% | |
| 68.3% | 78% | 65% | 62% | 62% | 74% | 55% | 64% | 69% | 59% | 78% | 79% | 58% | 65% | 75% | 75% | 76% | 75% | 75% | 58% | 62% | 71% | |
| 67.2% | 70% | 70% | 70% | 71% | 70% | 61% | 70% | 67% | 65% | 70% | 67% | 61% | 66% | 67% | 67% | 70% | 66% | 73% | 66% | 62% | 62% | |
| 62.1% | 68% | 71% | 71% | 71% | 82% | 52% | 49% | 49% | 58% | 65% | 58% | 52% | 65% | 52% | 71% | 68% | 56% | 67% | 52% | 59% | 68% | |
| 61.7% | 73% | 70% | 72% | 56% | 72% | 56% | 52% | 56% | 64% | 61% | 66% | 56% | 56% | 61% | 69% | 66% | 64% | 69% | 56% | 46% | 54% |