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.
Tests whether models correctly apply community-specific language preferences rather than universal person-first or identity-first rules. Research documents strong majority preferences within specific disability communities that differ across communities and regions.
Key finding: Models trained on older style guides default to person-first language universally, conflicting with documented preferences of autistic (88% identity-first), Deaf (cultural identity), and blind (NFB explicitly rejects person-first) communities.
Sources:
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 Opus 4.1 | Claude Opus 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Deepseek Chat V3.1 | Deepseek R1 | Gemini 2.5 Flash | Gemini 2.5 Pro | Gemini 3 Pro Preview | Gemma 3 12b It | Gemma 3n E4b It | Llama 3 70b Instruct | Llama 4 Maverick | Meta Llama 3.1 405b Instruct Turbo | 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 5 | GPT 5.2 | GPT OSS 120b | GPT OSS 20b | O4 Mini | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | Grok 3 | Grok 4 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 27th 80.7% | 33rd 71.6% | 20th 87.9% | 8th 93.0% | 22nd 86.6% | 15th 90.3% | 10th 91.2% | 2nd 94.9% | 4th 93.9% | 12th 90.7% | 5th 93.9% | 1st 96.1% | 14th 90.4% | 30th 75.6% | 29th 76.7% | 35th 64.7% | 25th 84.7% | 26th 83.7% | 13th 90.4% | 21st 86.8% | 6th 93.8% | 28th 78.9% | 31st 75.0% | 32nd 74.1% | 34th 70.8% | 18th 88.3% | 11th 90.9% | 18th 88.3% | 24th 85.3% | 9th 91.9% | 3rd 94.2% | 16th 89.3% | 23rd 86.4% | 17th 89.0% | 6th 93.8% | |
| 91.5% | 68% | 72% | 83% | 92% | 97% | 97% | 89% | 100% | 100% | 100% | 100% | 100% | 98% | 94% | 59% | 100% | 100% | 100% | 100% | 100% | 73% | 73% | 83% | 61% | 95% | 100% | 94% | 97% | 97% | 100% | 96% | 94% | 100% | 100% | ||
| 90.5% | 98% | 83% | 97% | 100% | 94% | 78% | 90% | 97% | 98% | 93% | 94% | 100% | 98% | 73% | 93% | 45% | 100% | 91% | 98% | 87% | 96% | 82% | 92% | 56% | 75% | 97% | 92% | 98% | 92% | 94% | 100% | 98% | 98% | 97% | 94% | |
| 79.6% | 83% | 100% | 77% | 92% | 86% | 74% | 92% | 98% | 98% | 67% | 90% | 98% | 85% | 20% | 83% | 71% | 53% | 92% | 58% | 89% | 92% | 65% | 81% | 78% | 73% | 63% | 91% | 71% | 89% | 89% | 77% | 59% | 81% | 91% | ||
| 100.0% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | ||
| 94.4% | 92% | 81% | 92% | 97% | 96% | 100% | 97% | 96% | 93% | 100% | 97% | 100% | 94% | 96% | 93% | 85% | 96% | 96% | 96% | 96% | 96% | 88% | 78% | 89% | 96% | 100% | 94% | 97% | 97% | 96% | 100% | 95% | 96% | 96% | ||
| 80.5% | 58% | 17% | 100% | 96% | 50% | 100% | 100% | 100% | 96% | 100% | 100% | 100% | 93% | 93% | 24% | 86% | 56% | 88% | 81% | 100% | 54% | 68% | 69% | 40% | 100% | 100% | 67% | 73% | 93% | 100% | 70% | 100% | 64% | 100% | ||
| 54.7% | 67% | 38% | 67% | 71% | 63% | 67% | 67% | 67% | 67% | 56% | 67% | 67% | 56% | 14% | 44% | 26% | 35% | 61% | 44% | 63% | 67% | 44% | 28% | 39% | 44% | 43% | 63% | 63% | 44% | 63% | 67% | 67% | 43% | 67% | 67% |