claude-3-7-sonnet-thinking · Scale Labs · large ↗
Anthropic / MODEL EVIDENCE
claude-3-7-sonnet-thinking
2 benchmarks · 5 observations · 2 sources
Scores at a glance
2 benchmarks · large dot: claude-3-7-sonnet-thinking; small dots: closest models where reported
PolyMath ↗20.8%
Claude-3.7-sonnet-thinking† · PolyMath · PolyMath-Top · Mean accuracy across the published languages ↗
3 more reported results
36.7% · Claude-3.7-sonnet-thinking† · PolyMath · PolyMath-High · Mean accuracy across the published languages · PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts ↗
48.8% · Claude-3.7-sonnet-thinking† · PolyMath · PolyMath-Medium · Mean accuracy across the published languages · PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts ↗
90.8% · Claude-3.7-sonnet-thinking† · PolyMath · PolyMath-Low · Mean accuracy across the published languages · PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
There are not enough shared scored settings to identify close comparisons reliably.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts — published result table ↗
All 16 authors
Yiming Wang, Pei Zhang, Jialong Tang, Haoran Wei, Baosong Yang, Rui Wang, Chenshu Sun, Feitong Sun, Jiran Zhang, Junxuan Wu, Qiqian Cang, Yichang Zhang, Fei Huang, Junyang Lin, Fei Huang, Jingren Zhou
- Scale Labs — evaluation methodology and results ↗
Names used in source tables
Claude-3.7-sonnet-thinking† · claude-3-7-sonnet-thinking