Loading analysis results...
Please wait while we prepare the detailed comparison.
Please wait while we prepare the detailed comparison.
| 🏆 Best Hybrid Score | openai/gpt-4.1 | 89.8% |
| 📉 Worst Hybrid Score | openai/gpt-4o-mini | 82.0% |
| 🤔 Most Differentiating Prompt | User: Summarize the rights related to work, employment conditions, pay, and trade unions as specified in Article 23 of the UDHR. | σ = 0.07 |
| 👯 Most Semantically Similar Pair | openai/gpt-4.1-nano vs openai/gpt-4o | 94.8% |
A consolidated overview of performance and semantic consistency metrics.
Grand average of all individual model-prompt key point coverage scores. StdDev (±) reflects variability around this grand mean, also in percentage points. A smaller StdDev suggests more consistent coverage scores across all model-prompt pairs; a larger StdDev indicates more diverse performance.
Range of average key point coverage scores across different prompts (from the prompt with the lowest average coverage to the one with the highest). A large spread indicates substantial differences in how challenging prompts were or how models performed on them.
Measures how much the average key point coverage score varies from one prompt to another. A high value (e.g., >20-25%) suggests that average performance was quite different across prompts; a low value suggests more consistent average performance from prompt to prompt.
Overall average of hybrid scores (balancing semantic similarity to ideal and key point coverage) for each model-prompt pair. Higher is generally better. A smaller StdDev suggests more consistent hybrid performance across all model-prompt pairs.
Models: openrouter:anthropic/claude-3.5-haiku, openrouter:anthropic/claude-sonnet-4, openrouter:cohere/command-a, openrouter:deepseek/deepseek-chat-v3-0324, openrouter:google/gemini-2.5-flash-preview-05-20, openrouter:google/gemini-2.5-pro-preview-05-06, openrouter:mistralai/mistral-large-2411, openrouter:mistralai/mistral-medium-3, openrouter:openai/gpt-4.1-mini, openrouter:openai/gpt-4.1-nano, openrouter:openai/gpt-4.1, openrouter:openai/gpt-4o-mini, openrouter:openai/gpt-4o, openrouter:x-ai/grok-3-mini-beta, openrouter:x-ai/grok-3
E.g. udhr-article-1: User: What fundamental principles regarding human dignity, rights, reason, and conscience are establ...
Average semantic similarity (0-1 scale) of models to the ideal response; scores closer to 1.0 are better. The StdDev shows how consistently models achieve this. A very low StdDev (e.g., <0.05) often means models performed very similarly on this metric.
| Metric | Value | Explanation |
|---|---|---|
| Overall Average Key Point Coverage | 95.3% (±8.5%) | Grand average of all individual model-prompt key point coverage scores. StdDev (±) reflects variability around this grand mean, also in percentage points. A smaller StdDev suggests more consistent coverage scores across all model-prompt pairs; a larger StdDev indicates more diverse performance. |
| Avg. Prompt Coverage Range | 79% - 100% (Spread: 21 pp) | Range of average key point coverage scores across different prompts (from the prompt with the lowest average coverage to the one with the highest). A large spread indicates substantial differences in how challenging prompts were or how models performed on them. |
| StdDev of Avg. Prompt Coverage | 5.7% | Measures how much the average key point coverage score varies from one prompt to another. A high value (e.g., >20-25%) suggests that average performance was quite different across prompts; a low value suggests more consistent average performance from prompt to prompt. |
| Overall Average Hybrid Score | 86.9% (±5.7%) | Overall average of hybrid scores (balancing semantic similarity to ideal and key point coverage) for each model-prompt pair. Higher is generally better. A smaller StdDev suggests more consistent hybrid performance across all model-prompt pairs. |
| Number of Models Evaluated | 15 | Models: openrouter:anthropic/claude-3.5-haiku, openrouter:anthropic/claude-sonnet-4, openrouter:cohere/command-a, openrouter:deepseek/deepseek-chat-v3-0324, openrouter:google/gemini-2.5-flash-preview-05-20, openrouter:google/gemini-2.5-pro-preview-05-06, openrouter:mistralai/mistral-large-2411, openrouter:mistralai/mistral-medium-3, openrouter:openai/gpt-4.1-mini, openrouter:openai/gpt-4.1-nano, openrouter:openai/gpt-4.1, openrouter:openai/gpt-4o-mini, openrouter:openai/gpt-4o, openrouter:x-ai/grok-3-mini-beta, openrouter:x-ai/grok-3 |
| Number of Prompts Analyzed | 12 | E.g. udhr-article-1: User: What fundamental principles regarding human dignity, rights, reason, and conscience are establ... |
| Average Semantic Similarity to Ideal | 0.714 (±0.019) | Average semantic similarity (0-1 scale) of models to the ideal response; scores closer to 1.0 are better. The StdDev shows how consistently models achieve this. A very low StdDev (e.g., <0.05) often means models performed very similarly on this metric. |
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude 3.5 Haiku | Claude Sonnet 4 | Command A | Deepseek Chat V3 0324 | Gemini 2.5 Flash Preview 05 20 | Gemini 2.5 Pro Preview 05 06 | Mistral Large 2411 | Mistral Medium 3 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4.1 | GPT 4o Mini | GPT 4o | Grok 3 Mini Beta | Grok 3 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 10th 94.4% | 10th 94.4% | 5th 97.1% | 7th 96.1% | 2nd 99.3% | 12th 94.3% | 6th 96.7% | 8th 96.0% | 13th 92.9% | 15th 88.2% | 4th 98.4% | 14th 88.4% | 9th 94.8% | 1st 99.3% | 3rd 98.9% | |
| 98.5% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 78% | 100% | 100% | 100% | 100% | 100% | |
| 97.7% | 100% | 81% | 100% | 98% | 100% | 100% | 100% | 98% | 100% | 100% | 100% | 88% | 100% | 100% | 100% | |
| 98.7% | 100% | 96% | 100% | 100% | 100% | 100% | 100% | 98% | 100% | 90% | 100% | 96% | 100% | 100% | 100% | |
| 99.5% | 95% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 98% | 100% | 100% | |
| 91.9% | 84% | 92% | 100% | 89% | 100% | 100% | 98% | 100% | 72% | 86% | 100% | 72% | 88% | 100% | 98% | |
| 96.7% | 98% | 95% | 100% | 100% | 100% | 100% | 100% | 100% | 98% | 88% | 98% | 80% | 93% | 100% | 100% | |
| 95.0% | 91% | 100% | 100% | 99% | 100% | 100% | 100% | 91% | 90% | 78% | 100% | 76% | 100% | 100% | 100% | |
| 100.0% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | |
| 100.0% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | |
| 94.5% | 100% | 100% | 100% | 88% | 100% | 97% | 88% | 88% | 88% | 100% | 100% | 88% | 81% | 100% | 100% | |
| 78.9% | 77% | 77% | 79% | 88% | 91% | 68% | 74% | 82% | 70% | 55% | 83% | 73% | 80% | 94% | 92% | |
| 91.9% | 88% | 92% | 86% | 91% | 100% | 66% | 100% | 95% | 97% | 83% | 100% | 88% | 98% | 98% | 97% |