Claude Sonnet 5
Comprehensive benchmark performance across 11 evaluation categories
Composite Score
0.0/100Rank
Token Benchmark
100.0Lower burn, higher score
Total Tokens
~8.9k/test
Category Radar
The full radar chart is shown on wider screens. On mobile, the category breakdown below provides the same values in a readable stacked layout.
Historical Composite Score
Category Breakdown
| # | Category | Score | Tests | 7-Day Trend | Weight |
|---|---|---|---|---|---|
| 1 | Token Efficiency | 100.0 | 30 | 1.0x | |
| 2 | Feature Implementation | 96.7 | 3 | 1.0x | |
| 3 | Bug Fixes | 95.7 | 3 | 1.0x | |
| 4 | Coding Tasks | 94.7 | 3 | 1.0x | |
| 5 | Performance & Efficiency | 92.3 | 3 | 1.0x | |
| 6 | Bug Introduction Rate | 90.7 | 3 | 1.0x | |
| 7 | Code Quality | 89.7 | 3 | 1.0x | |
| 8 | Security Awareness | 89.3 | 3 | 1.0x | |
| 9 | Code Thoroughness | 86.2 | 3 | 1.0x | |
| 10 | Instruction Following | 82.7 | 3 | 1.0x | |
| 11 | Long Reasoning | 51.6 | 3 | 1.0x |
Individual Test Results
Token Efficiency is computed from every successful task in the run. The model with the lowest average token burn receives 100, and heavier token usage is penalized proportionally.
Avg Tokens/Test
8.9k
Total Tokens
267.2k
Regression History
18Score dropped -13.2% from 95.3 to 82.7
Score dropped -3.9% from 87.9 to 84.5
Score dropped -7.9% from 89.8 to 82.7
Score dropped -27.9% from 93.3 to 67.3
Score dropped -4.5% from 90.4 to 86.3
Score dropped -4.3% from 94.0 to 90.0
Score dropped -3.9% from 90.8 to 87.3
Score dropped -5.5% from 92.8 to 87.7
Score dropped -6.3% from 96.1 to 90.1
Score dropped -6.6% from 86.9 to 81.2
Score dropped -28.7% from 91.2 to 65.0
Score dropped -3.2% from 91.7 to 88.7
Score dropped -4.1% from 84.0 to 80.6
Score dropped -3.2% from 91.2 to 88.3
Score dropped -3.5% from 90.5 to 87.3
Score dropped -6.1% from 94.5 to 88.7
Score dropped -3.4% from 91.4 to 88.3
Score dropped -28.8% from 64.3 to 45.8