claude-sonnet-5.5
Benchmark profile · LiveBench 2.0 ·
Results for this model
- Overall benchmark score
- 81.0 / 100
- Cost per task
- $3.3139
- Cost per success
- $4.0906
- Coding
- 94.7 / 100
- Reasoning
- 91.6 / 100
- Browser use
- 89.3 / 100
Costs are based on the benchmark’s 471 shared tasks. Cost per success adjusts the reported cost by the model’s overall score.