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 India. Source: Global Dialogues GD2 (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 | 10th 81.0% | 1st 85.0% | 7th 82.7% | 4th 84.0% | 19th 75.3% | 18th 75.7% | 17th 77.3% | 21st 74.7% | 5th 83.3% | 3rd 84.3% | 12th 80.7% | 10th 81.0% | 9th 82.0% | 16th 78.0% | 14th 80.0% | 13th 80.3% | 20th 75.0% | 8th 82.3% | 2nd 84.3% | 15th 79.3% | 6th 83.0% | |
| 88.5% | 94% | 93% | 96% | 96% | 71% | 88% | 87% | 76% | 87% | 90% | 87% | 95% | 93% | 80% | 82% | 90% | 85% | 94% | 87% | 94% | 94% | |
| 76.5% | 75% | 81% | 79% | 78% | 78% | 76% | 70% | 69% | 81% | 81% | 79% | 70% | 76% | 72% | 85% | 78% | 67% | 80% | 85% | 66% | 80% | |
| 76.3% | 74% | 81% | 73% | 78% | 77% | 63% | 75% | 79% | 82% | 82% | 76% | 78% | 77% | 82% | 73% | 73% | 73% | 73% | 81% | 78% | 75% |