Claude Opus 5
Comprehensive benchmark performance across 11 evaluation categories
Composite Score
0.0/100Rank
Token Benchmark
66.7Lower burn, higher score
Total Tokens
~13.4k/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 | Bug Fixes | 98.4 | 3 | 1.0x | |
| 2 | Bug Introduction Rate | 95.3 | 3 | 1.0x | |
| 3 | Instruction Following | 94.7 | 3 | 1.0x | |
| 4 | Feature Implementation | 94.3 | 3 | 1.0x | |
| 5 | Coding Tasks | 93.0 | 3 | 1.0x | |
| 6 | Performance & Efficiency | 92.7 | 3 | 1.0x | |
| 7 | Code Quality | 87.7 | 3 | 1.0x | |
| 8 | Security Awareness | 85.5 | 3 | 1.0x | |
| 9 | Code Thoroughness | 84.5 | 3 | 1.0x | |
| 10 | Token Efficiency | 66.7 | 30 | 1.0x | |
| 11 | Long Reasoning | 46.2 | 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
13.4k
Total Tokens
400.6k
Regression History
19Score dropped -4.0% from 92.4 to 88.7
Score dropped -4.7% from 90.2 to 85.9
Score dropped -5.1% from 89.6 to 85.0
Score dropped -6.8% from 85.6 to 79.8
Score dropped -3.7% from 93.2 to 89.7
Score dropped -10.4% from 91.4 to 81.9
Score dropped -13.3% from 93.8 to 81.3
Score dropped -5.7% from 87.3 to 82.4
Score dropped -3.5% from 94.4 to 91.1
Score dropped -3.3% from 86.5 to 83.6
Score dropped -22.0% from 94.5 to 73.7
Score dropped -10.7% from 93.0 to 83.0
Score dropped -3.4% from 92.9 to 89.7
Score dropped -14.7% from 70.7 to 60.3
Score dropped -4.1% from 93.5 to 89.7
Score dropped -3.9% from 91.2 to 87.7
Score dropped -4.9% from 90.1 to 85.7
Score dropped -5.0% from 87.9 to 83.5
Score dropped -31.8% from 62.7 to 42.8