Anthropic's strongest generally available model, cheaper and up to 30% faster than Fable 5.1, with large gains on long-running agentic, scientific, and hardware design work.
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 4 benchmarks where scores spread out.
| Benchmark | Score | Rank |
|---|---|---|
HLEArtificial Analysis Challenging multidisciplinary questions evaluated by Artificial Analysis | 74.3% | #1 / 103 |
ARC-AGIARC Prize Novel reasoning tasks requiring fluid intelligence | 98.8% | #2 / 41 |
| Benchmark / source | Score |
|---|---|
HLE Artificial AnalysisClaude Fable 5.2 (Max, Default Fallback) | 74.3% |
Terminal-Bench 4.0 Artificial AnalysisClaude Fable 5.2 (Max, Default Fallback) | 59.6% |
SciCode Artificial AnalysisClaude Fable 5.2 (Max, Default Fallback) | 67.7% |
AA-LCR Artificial AnalysisClaude Fable 5.2 (Max, Default Fallback) | 83.3% |
CritPt Artificial AnalysisClaude Fable 5.2 (Max, Default Fallback) | 35.4% |