TutorBench ↗45.46%
claude-opus-4-20250514 · Scale Labs · Score ↗
Anthropic / MODEL EVIDENCE
Claude Opus 4-20250514
4 benchmarks · 5 observations · 4 sources
Scores at a glance
4 benchmarks · large dot: Claude Opus 4-20250514; small dots: closest models where reported
claude-opus-4-20250514 (32k thinking) · Aider coding benchmarks · Polyglot · percent correct ↗
SEAL Showdown ↗1065.8 Elo
claude-opus-4-20250514 · SEAL Showdown · style-controlled Elo · 2025-09-20 · September 20, 2025 snapshot ↗
1 more reported result
1039.3 Elo · claude-opus-4-20250514 (Thinking) · SEAL Showdown · style-controlled Elo · 2025-09-20 · September 20, 2025 snapshot · SEAL Showdown Technical Report ↗
claude-opus-4-20250514 · FrontierMath-2025-02-28-Public · FrontierMath public · 10 questions · source run score · Epoch AI · public February 2025 sample · historical release ↗
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.
- Aider code editing benchmark ↗
- Scale Labs — evaluation methodology and results ↗
- A Rosetta Stone for AI Benchmarks — released Epoch evaluation runs ↗
- SEAL Showdown Technical Report ↗
Names used in source tables
claude-opus-4-20250514 · claude-opus-4-20250514 (32k thinking) · claude-opus-4-20250514 (Thinking)