Model detail
Qwen3.7 Plus
Provider: Alibaba · Public slug: qwen-qwen3-7-plus
- Rank
- 23
- Rank movement
- Baseline
- Score
- 29.0
- Last measured
- 2026-07-05
- Coverage
- XHigh not supported
Reasoning scores
- XHigh
- —
- Medium
- 39.6
- None
- 18.4
Generation health
Medium13%62%25%n 8None45%22%33%n 9 XHigh not supportedHigh repair rateHigh failure rateCost summary
- Mean standard list-price equivalent
- $0.03
- Median unique-cell cost
- $0.01
- Unique-cell range
- $0.0052–$0.09
- Coverage
- 16 unique cells / 17 observed runs
- Observed-run total
- $0.52
- Evidence basis
- Provider-reported
- Mean output
- 20k tok
- Output range
- 2.3k–63k tok
- Token samples
- 17
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