Model detail
Claude Opus 4.5
Provider: Anthropic · Public slug: claude-opus-4-5
- Rank
- 9
- Rank movement
- Baseline
- Score
- 41.9
- Last measured
- 2026-07-05
- Coverage
- Complete coverage
Reasoning scores
- XHigh
- 42.4
- Medium
- 37.2
- None
- 45.9
Generation health
XHigh75%13%12%n 8Medium100%0%0%n 8None100%0%0%n 8 Complete coverageCost summary
- Mean standard list-price equivalent
- $0.21
- Median unique-cell cost
- $0.23
- Unique-cell range
- $0.10–$0.38
- Coverage
- 24 unique cells / 24 observed runs
- Observed-run total
- $5.07
- Evidence basis
- Standard list-price estimate
- Mean output
- 6.5k tok
- Output range
- 2.1k–12k tok
- Token samples
- 24
Cost means equal-weight unique model/game/reasoning cells. Provider-account billed spend is reported separately on Charts.
Run setup
- Overall Models: combines public reasoning variants
- Standard GameBench code-generation prompt