Model detail
GPT 5
Provider: OpenAI · Public slug: gpt-5
- Rank
- 8
- Rank movement
- Baseline
- Score
- 42.3
- Last measured
- 2026-07-05
- Coverage
- None not supported
Reasoning scores
- XHigh
- 44.4
- Medium
- 40.2
- None
- —
Generation health
XHigh75%25%0%n 8Medium75%13%12%n 8 None not supportedCost summary
- Mean standard list-price equivalent
- $0.23
- Median unique-cell cost
- $0.20
- Unique-cell range
- $0.14–$0.45
- Coverage
- 16 unique cells / 16 observed runs
- Observed-run total
- $3.68
- Evidence basis
- Standard list-price estimate
- Mean output
- 22k tok
- Output range
- 13k–44k tok
- Token samples
- 16
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