Statistical analysis of how 293 AI model composite scores are distributed. Explore the mean, median, percentiles, and tier breakdowns to understand the AI model landscape.
Summary statistics across all 293 scored models.
Mean Score
49.1
+/- 12.0 stddev
Median Score
47.8
Score Range
17—91
95th Percentile
68.3
Above Median
149
of 293 models
Number of models in each 10-point score bucket.
Models grouped by performance tier with summary statistics.
| Tier | Range | Count | % of Total |
|---|---|---|---|
| Elite | 90–100 | 1 | 0.3% |
| Strong | 70–89 | 7 | 2.4% |
| Average | 50–69 | 108 | 36.9% |
| Below Average | 30–49 | 147 | 50.2% |
| Weak | 0–29 | 9 | 3.1% |
Score thresholds at key percentile levels.
| Percentile | Score | Position |
|---|---|---|
| P5 | 30.2 | 1791 |
| P10 | 34.1 | 1791 |
| P25 | 42.2 | 1791 |
| P50 | 47.8 | 1791 |
| P75 | 56.4 | 1791 |
| P90 | 64.7 | 1791 |
| P95 | 68.3 | 1791 |
Providers with 3+ models, ranked by average composite score.
| Provider | Models | Avg Score |
|---|---|---|
1Anthropic | 13 | 62.1 |
2ByteDance | 4 | 56.3 |
3OpenAI | 59 | 56.1 |
4xAI | 8 | 53.9 |
5Google | 24 | 53.7 |
6NVIDIA | 8 | 50.1 |
7Alibaba | 51 | 49.6 |
8Inception | 3 | 48.4 |
9MiniMax | 6 | 48.3 |
10Amazon | 5 | 47.6 |
How models are distributed across the top 20%, middle 60%, and bottom 20% of scores.
How scores are computed and what the distribution reveals.
Each model receives a composite score from 0 to 100, calculated as a weighted combination of six signals: capabilities (25%), pricing tier (25%), context window (15%), recency (15%), output capacity (10%), and versatility (10%). The score is designed to capture overall model quality and value in a single number.
The score distribution reveals the competitive landscape of AI models. A tight cluster near the median suggests many similarly capable models, while a wide spread indicates clear differentiation between tiers. The shape of the distribution, its skew, and the gap between mean and median all provide insight into whether the market is top-heavy, bottom-heavy, or evenly distributed.
Continue exploring AI model data with benchmarks, capabilities, and the full leaderboard.