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.
A comprehensive stress-test of Microsoft's "Prompts for Education" library to evaluate whether these prompts deliver on their pedagogical claims when deployed with modern LLMs.
Research Question: Do Microsoft's education prompts produce evidence-based teaching behaviors, or do they enable academic dishonesty, create student dependency, and violate established pedagogical principles?
Source Material: Microsoft Prompts for Education Repository
Testing Methodology:
Each Microsoft prompt is tested in two deployment modes:
Evaluation Criteria:
We test whether these prompts achieve their stated goals while maintaining:
Key Findings to Test:
Critical Context:
Microsoft presents these prompts as effective educational tools aligned with their Responsible AI principles (Fairness, Reliability, Safety, Inclusiveness, Transparency, Accountability). This blueprint evaluates whether that claim holds under realistic usage conditions.
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude 3.5 Sonnet | Claude 3.7 Sonnet | Claude 3.5 Haiku | Claude Haiku 4.5 | Claude Opus 4.1 | Claude Sonnet 4 | Claude Sonnet 4.5 | Deepseek Chat V3.1 | Deepseek R1 | Gemini 2.5 Flash | Gemini 2.5 Pro | Gemma 3 12b 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 OSS 120b | GPT OSS 20b | O4 Mini | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | Grok 3 | Grok 4 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 7th 79.2% | 19th 70.8% | 3rd 83.7% | 6th 81.5% | 4th 83.3% | 1st 83.8% | 1st 83.8% | 18th 71.1% | 23rd 66.5% | 5th 82.2% | 14th 71.9% | 8th 75.0% | 20th 70.2% | 10th 74.5% | 25th 65.1% | 22nd 68.7% | 16th 71.1% | 31st 54.3% | 21st 69.9% | 11th 73.5% | 29th 59.2% | 26th 63.5% | 13th 71.9% | 9th 74.9% | 28th 60.0% | 30th 58.6% | 15th 71.5% | 24th 65.4% | 27th 62.8% | 32nd 52.0% | 12th 72.2% | 17th 71.1% | |
| 93.8% | 100% | 86% | 100% | 86% | 100% | 100% | 100% | 100% | 79% | 100% | 100% | 100% | 71% | 100% | 100% | 100% | 93% | 86% | 100% | 100% | 100% | 86% | 100% | 100% | 93% | 64% | 100% | 100% | 86% | 71% | 100% | 100% | |
| 69.7% | 77% | 59% | 97% | 82% | 70% | 68% | 64% | 67% | 75% | 75% | 73% | 86% | 88% | 59% | 76% | 64% | 71% | 56% | 67% | 70% | 67% | 50% | 60% | 70% | 76% | 17% | 68% | 63% | 83% | 90% | 56% | 88% | |
| 63.0% | 57% | 71% | 83% | 77% | 73% | 80% | 69% | 61% | 50% | 86% | 54% | 77% | 66% | 80% | 57% | 55% | 63% | 69% | 56% | 57% | 53% | 51% | 54% | 67% | 51% | 52% | 61% | 50% | 76% | 54% | 51% | 56% | |
| 91.2% | 95% | 95% | 100% | 91% | 95% | 99% | 95% | 73% | 91% | 100% | 90% | 80% | 100% | 86% | 100% | 100% | 73% | 100% | 100% | 100% | 66% | 86% | 86% | 100% | 95% | 94% | 95% | 95% | 100% | 68% | 86% | 85% | |
| 71.1% | 89% | 80% | 81% | 72% | 90% | 74% | 83% | 75% | 92% | 92% | 79% | 81% | 58% | 48% | 48% | 74% | 85% | 28% | 83% | 68% | 40% | 63% | 63% | 100% | 48% | 38% | 75% | 92% | 80% | 48% | 73% | 74% | |
| 81.7% | 90% | 95% | 93% | 96% | 100% | 94% | 100% | 93% | 93% | 90% | 100% | 100% | 65% | 53% | 60% | 100% | 94% | 0% | 96% | 73% | 53% | 60% | 71% | 100% | 60% | 48% | 48% | 96% | 100% | 100% | 100% | 92% | |
| 75.7% | 80% | 95% | 95% | 95% | 95% | 86% | 83% | 95% | 100% | 100% | 91% | 70% | 58% | 100% | 53% | 58% | 45% | 25% | 13% | 75% | 50% | 86% | 50% | 38% | 75% | 75% | 70% | 88% | 100% | 91% | 100% | 86% | |
| 89.1% | 86% | 93% | 93% | 100% | 96% | 92% | 98% | 96% | 93% | 93% | 81% | 88% | 96% | 96% | 79% | 86% | 96% | 89% | 82% | 79% | 77% | 81% | 84% | 89% | 96% | 80% | 89% | 89% | 96% | 81% | 82% | 96% | |
| 55.8% | 60% | 54% | 60% | 70% | 66% | 60% | 58% | 50% | 36% | 70% | 66% | 68% | 70% | 50% | 20% | 40% | 54% | 40% | 64% | 60% | 30% | 76% | 60% | 60% | 50% | 60% | 49% | 50% | 61% | 34% | 80% | 60% | |
| 50.0% | 50% | 50% | 40% | 40% | 60% | 60% | 63% | 61% | 40% | 60% | 60% | 56% | 60% | 60% | 60% | 40% | 50% | 50% | 40% | 50% | 40% | 56% | 40% | 60% | 40% | 40% | 53% | 60% | 40% | 20% | 50% | 50% | |
| 93.3% | 97% | 97% | 100% | 94% | 93% | 98% | 94% | 97% | 69% | 85% | 97% | 97% | 100% | 97% | 100% | 93% | 94% | 73% | 95% | 93% | 93% | 97% | 93% | 97% | 78% | 92% | 97% | 98% | 93% | 99% | 88% | 98% | |
| 45.0% | 34% | 27% | 41% | 32% | 36% | 80% | 52% | 40% | 27% | 76% | 44% | 73% | 34% | 50% | 39% | 43% | 53% | 52% | 43% | 43% | 44% | 40% | 48% | 33% | 27% | 57% | 85% | 35% | 27% | 35% | 41% | 49% | |
| 78.1% | 72% | 86% | 71% | 79% | 79% | 86% | 81% | 79% | 86% | 71% | 71% | 86% | 79% | 71% | 86% | 78% | 79% | 81% | 86% | 79% | 86% | 81% | 71% | 71% | 67% | 71% | 67% | 86% | 81% | 64% | 81% | 86% | |
| 57.2% | 76% | 8% | 42% | 79% | 86% | 71% | 73% | 100% | 42% | 69% | 67% | 25% | 89% | 100% | 67% | 61% | 65% | 25% | 67% | 70% | 17% | 71% | 84% | 69% | 50% | 58% | 68% | 8% | 0% | 8% | 50% | 67% | |
| 64.4% | 87% | 88% | 96% | 76% | 86% | 93% | 96% | 68% | 1% | 90% | 100% | 20% | 84% | 100% | 73% | 70% | 80% | 0% | 60% | 63% | 90% | 64% | 80% | 60% | 64% | 64% | 63% | 0% | 1% | 0% | 76% | 68% | |
| 58.8% | 64% | 56% | 100% | 67% | 52% | 56% | 71% | 47% | 83% | 42% | 45% | 50% | 60% | 77% | 45% | 78% | 78% | 76% | 58% | 42% | 67% | 42% | 83% | 50% | 42% | 42% | 42% | 42% | 75% | 67% | 33% | 50% | |
| 79.7% | 86% | 71% | 86% | 81% | 86% | 63% | 86% | 69% | 100% | 71% | 71% | 86% | 86% | 71% | 84% | 86% | 84% | 86% | 81% | 86% | 84% | 76% | 86% | 71% | 67% | 67% | 71% | 86% | 86% | 86% | 86% | 63% | |
| 45.4% | 69% | 58% | 81% | 90% | 100% | 100% | 90% | 8% | 20% | 54% | 8% | 34% | 20% | 14% | 20% | 20% | 14% | 8% | 79% | 60% | 58% | 20% | 55% | 70% | 55% | 8% | 74% | 8% | 8% | 8% | 84% | 58% | |
| 38.4% | 81% | 0% | 96% | 96% | 86% | 84% | 100% | 4% | 3% | 100% | 1% | 92% | 4% | 94% | 5% | 0% | 0% | 0% | 0% | 73% | 3% | 0% | 90% | 61% | 0% | 66% | 80% | 0% | 1% | 1% | 4% | 3% | |
| 86.1% | 97% | 100% | 100% | 100% | 100% | 100% | 97% | 100% | 100% | 97% | 97% | 100% | 94% | 71% | 97% | 100% | 94% | 85% | 97% | 97% | 50% | 64% | 89% | 100% | 50% | 64% | 64% | 100% | 30% | 24% | 97% | 100% | |
| 73.2% | 96% | 89% | 95% | 89% | 84% | 100% | 96% | 86% | 87% | 100% | 100% | 86% | 68% | 62% | 79% | 66% | 100% | 75% | 70% | 80% | 40% | 48% | 40% | 86% | 41% | 40% | 53% | 92% | 67% | 9% | 75% | 43% | |
| 95.3% | 100% | 100% | 91% | 100% | 100% | 100% | 95% | 95% | 95% | 88% | 86% | 95% | 95% | 100% | 85% | 100% | 100% | 90% | 100% | 98% | 95% | 100% | 95% | 96% | 95% | 93% | 100% | 100% | 90% | 85% | 95% | 93% |