Claude Opus 4.8
Comprehensive benchmark performance across 11 evaluation categories
Composite Score
0.0/100Rank
Token Benchmark
100.0Lower burn, higher score
Total Tokens
~7.7k/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 | Instruction Following | 100.0 | 3 | 1.0x | |
| 3 | Coding Tasks | 99.3 | 3 | 1.0x | |
| 4 | Feature Implementation | 99.3 | 3 | 1.0x | |
| 5 | Bug Introduction Rate | 97.0 | 3 | 1.0x | |
| 6 | Bug Fixes | 96.3 | 3 | 1.0x | |
| 7 | Performance & Efficiency | 94.0 | 3 | 1.0x | |
| 8 | Security Awareness | 90.1 | 3 | 1.0x | |
| 9 | Code Thoroughness | 89.9 | 3 | 1.0x | |
| 10 | Code Quality | 82.7 | 3 | 1.0x | |
| 11 | Long Reasoning | 66.3 | 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
7.7k
Total Tokens
231.9k
Regression History
11Score dropped -6.1% from 69.1 to 64.9
Score dropped -3.3% from 98.2 to 95.0
Score dropped -13.5% from 97.0 to 83.9
Score dropped -3.0% from 99.0 to 96.0
Score dropped -4.6% from 68.9 to 65.7
Score dropped -4.1% from 98.8 to 94.7
Score dropped -10.7% from 91.6 to 81.8
Score dropped -27.3% from 99.0 to 72.0
Score dropped -3.3% from 93.8 to 90.7
Score dropped -25.6% from 91.8 to 68.3
Score dropped -3.9% from 66.5 to 63.9