Second model of the Claude 5.5 family. Anthropic reports over 30% faster output and up to 30% lower cost per task than Sonnet 5 at the same $2/$10 pricing.
SI v3 uses weighted percentages from one Artificial Analysis configuration. Ranking requires all five benchmarks. Partial scores average only available weights. Scores are not comparable to SI v2 or a probability of reaching singularity.
Compared with 58 models released within six months of it, across 3 benchmarks where scores spread out.
| Benchmark | Score | Rank |
|---|---|---|
HLEArtificial Analysis Challenging multidisciplinary questions evaluated by Artificial Analysis | 55% | #5 / 95 |
| Benchmark / source | Score |
|---|---|
HLE Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback) | 55% |
Terminal-Bench 4.0 Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback) | 63.6% |
SciCode Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback) | 61% |
AA-LCR Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback) | 82.7% |
CritPt Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback) | 31.4% |