Claude Sonnet 4.6 · Vending-Bench(2),Vending-Bench 2 max effort配置,Final bank balance $7,204.14 USD(具体成绩公布时间未确认)。见《Claude Sonnet 4.6 System Card》§2.13, PDF p.27。 查看成绩条件
Claude Sonnet 4.6 · Vending-Bench(2),Vending-Bench 2 high effort配置,Final bank balance $6,625.10 USD(具体成绩公布时间未确认)。见《Claude Sonnet 4.6 System Card》§2.13, PDF p.27。 查看成绩条件
Claude Sonnet 4.6 · Vending-Bench(2),Vending-Bench 2 max effort配置,Mean run cost $265.03 USD(具体成绩公布时间未确认)。见《Claude Sonnet 4.6 System Card》§2.13, PDF p.27。 查看成绩条件
Sonnet 4.6 achieved a final balance of $7,204.14 with Max effort and $6,625.10 with High effort compared to Claude Opus 4.6’s SOTA of $8,017.59. At Max effort the mean cost of a Sonnet 4.6 run was $265.03, compared to Opus 4.6’s $682.37.
PDF with changelog dated 2026-03-06; 135 pages; collected 2026-11-10
版本公布
未确认
披露时间
未确认 · 首发/后补未确认
采集时间
历史依据
暂无可靠历史版本依据
引用文本
Claude Sonnet 4.6 · Vending-Bench(2),Vending-Bench 2 max effort配置,Final bank balance $7,204.14 USD(具体成绩公布时间未确认);Claude Sonnet 4.6 · Vending-Bench(2),Vending-Bench 2 high effort配置,Final bank balance $6,625.10 USD(具体成绩公布时间未确认);Claude Sonnet 4.6 · Vending-Bench(2),Vending-Bench 2 max effort配置,Mean run cost $265.03 USD(具体成绩公布时间未确认)。官方出处 Claude Sonnet 4.6 System Card(附件,PDF with changelog dated 2026-03-06; 135 pages; collected 2026-11-10)§2.13, PDF p.27,https://www.anthropic.com/claude-sonnet-4-6-system-card#page=27。Benchlog https://benchlog.lekshome.cc/evidence/claude-sonnet-4-6/ev46-vending2/
关联成绩与条件
Claude Sonnet 4.6 · Vending-Bench 成绩与配置
指标与成绩
配置与评测条件
证据关系
Final bank balance$7,204.14 USD原文 $7,204.14 · 单位 USD
公布 未确认
Vending-Bench 2 max effort
设置
Max effort as named for this benchmark.
未知项
The report does not state whether adaptive thinking was enabled.
Claude Sonnet 4.6 · Vending-Bench (2), configuration Vending-Bench 2 max effort, Final bank balance $7,204.14 USD (exact score publication date unconfirmed). See “Claude Sonnet 4.6 System Card” at §2.13, PDF p.27. View score conditions
Claude Sonnet 4.6 · Vending-Bench (2), configuration Vending-Bench 2 high effort, Final bank balance $6,625.10 USD (exact score publication date unconfirmed). See “Claude Sonnet 4.6 System Card” at §2.13, PDF p.27. View score conditions
Claude Sonnet 4.6 · Vending-Bench (2), configuration Vending-Bench 2 max effort, Mean run cost $265.03 USD (exact score publication date unconfirmed). See “Claude Sonnet 4.6 System Card” at §2.13, PDF p.27. View score conditions
Sonnet 4.6 achieved a final balance of $7,204.14 with Max effort and $6,625.10 with High effort compared to Claude Opus 4.6’s SOTA of $8,017.59. At Max effort the mean cost of a Sonnet 4.6 run was $265.03, compared to Opus 4.6’s $682.37.
PDF with changelog dated 2026-03-06; 135 pages; collected 2026-11-10
Version published
Unconfirmed
Disclosure date
Unconfirmed · Launch or later disclosure unconfirmed
Collected
Historical basis
No reliable historical version evidence available
Citation text
Claude Sonnet 4.6 · Vending-Bench (2), configuration Vending-Bench 2 max effort, Final bank balance $7,204.14 USD (exact score publication date unconfirmed); Claude Sonnet 4.6 · Vending-Bench (2), configuration Vending-Bench 2 high effort, Final bank balance $6,625.10 USD (exact score publication date unconfirmed); Claude Sonnet 4.6 · Vending-Bench (2), configuration Vending-Bench 2 max effort, Mean run cost $265.03 USD (exact score publication date unconfirmed). Official source: Claude Sonnet 4.6 System Card (Attachment, PDF with changelog dated 2026-03-06; 135 pages; collected 2026-11-10), §2.13, PDF p.27, https://www.anthropic.com/claude-sonnet-4-6-system-card#page=27. Benchlog https://benchlog.lekshome.cc/evidence/claude-sonnet-4-6/ev46-vending2/?lang=en
Related scores and conditions
Claude Sonnet 4.6 · Vending-Bench scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
Final bank balance$7,204.14 USDReported $7,204.14 · Unit USD
Published Unconfirmed
Vending-Bench 2 max effort
Settings
Max effort as named for this benchmark.
Unknowns
The report does not state whether adaptive thinking was enabled.