Gemini 4 Carbon

Google·4 个数据来源·更新于 2026-11-10

上下文窗口1MArtificial Analysis
输入 / 百万 Token$4Artificial Analysis
输出 / 百万 Token$20Artificial Analysis

评测表现

只在同一来源、同一口径下比较。切换来源可查看不同测试结果。

4 个评测来源

当前配置:各基准设置见下表

采集于 2026-11-10查看原始页面

综合分数和同榜图表来自 LLM Stats 榜单(采集于 2026-11-10);下方逐项成绩来自模型页。榜单出处

LLM Stats · LLM Stats Score
57.5原榜第 4 名

同榜模型表现

LLM Stats Score · 同一来源与榜单口径,分数越高越好

7 个配置
所选配置其他配置
查看完整对比数据
模型与配置LLM Stats Score每任务成本
Claude Fable 5.261.3未公布
Claude Mythos 5.259.6未公布
Claude Opus 5.558.9未公布
Gemini 4 Carbon · 当前模型57.5未公布
Claude Sonnet 5.557.2未公布
GPT-6 Astra56.8未公布
Kimi K3.1 Pro55.1未公布

不同来源的分数不能直接相加或横向比较;评测任务成本不是 API Token 单价。

逐项基准成绩

16 项已收录成绩 · 保留原始单位和测试条件

AutomationBench厂商自报 · 越高越好
53.9%

Private set; sourced from the official Zapier public leaderboard.

成绩出处
Blueprint-Bench 2厂商自报 · 越高越好
58.6%

Similarity score; reported from the Andon Labs official public leaderboard.

成绩出处
Chartography (no tools)厂商自报 · 越高越好
72.5%

Without tools; follows the official Surge public leaderboard.

成绩出处
CWE-Bench厂商自报 · 越高越好
71%

CWE-bench v1; programmatic pass@1 from the official public leaderboard evaluated by Collinear AI (ties broken by pass@4). Evaluated without guardrails.

成绩出处
ExploitGym厂商自报 · 越高越好
53.5%

Default 6-hour timeout per task; single attempt per task; Antigravity harness; no internet; mitigations off; LLM judge verifies intended vulnerability; self-computed.

成绩出处
FrontierSWE V2厂商自报 · 越高越好
61.2%

FrontierSWE 2; reported from Proximal's official public leaderboard.

成绩出处
Graphwalks BFS >128k厂商自报 · 越高越好
96.2%

256k to 1M subset (200 problems); BFS (F1); self-computed.

成绩出处
Gray Swan IPI Benchmark厂商自报 · 越高越好
0%

Attack success rate at k=15 attempts (ASR@15); lower is better. Gemini 4 Argon: 0.7% on the same chart.

成绩出处
OSWorld 2.1 (partial)厂商自报 · 越高越好
81.5%

OSWorld 2.1 offline subset (82 tasks) partial score; maxed over 3 runs, single attempt per run; updated Gemini CUA harness with parallel batch tool calling; self-computed.

成绩出处
RiemannBench厂商自报 · 越高越好
80%

Reported from the official Surge public leaderboard.

成绩出处
SEC-bench Pro厂商自报 · 越高越好
88.2%

Pass@1 on the 183-task May 2026 JavaScript engine split, averaged over 3 attempts; Antigravity harness; self-computed.

成绩出处
Terminal-Bench 4.0-AA厂商自报 · 越高越好
65.2%

Terminal-Bench 4.0 (AA); third-party-run result as reported in Google's evals table.

成绩出处
Terminal-Bench-Science 0.1厂商自报 · 越高越好
64.8%

Terminal-Bench-Science 0.1; third-party-run result as reported in Google's evals table (not self-computed by Google).

成绩出处
Vals Index厂商自报 · 越高越好
70.4%

Vals Index v2.2; sourced from Vals AI. Highest thinking settings.

成绩出处
Vending-Bench 2厂商自报 · 越高越好
1,648,400%

Final bank balance (USD); reported from the Andon Labs official public leaderboard.

成绩出处
WebDev Arena厂商自报 · 越高越好
1,768分

Arena.ai WebDev Arena Elo 1768 for Gemini 4 Carbon (High); preliminary rating, CI ±15 (+15/-15) (2,230 votes); #4 (rank spread 2-6); +89 Elo over Gemini 4 Argon (High) at 1679.

成绩出处

技术规格

只展示有可靠来源的资料;优先采用厂商官网与官方模型仓库。

发布日期
2026-10-28LLM Stats
上下文窗口
1M TokenArtificial Analysis
开放权重
否Artificial Analysis
推理模式
支持Artificial Analysis
许可证
ProprietaryLLM Stats

价格与用量

美元 / 百万 Token。不同服务商或测试配置的报价分别列出。

模型 API 价格,单位为美元每百万 Token
来源 / 服务商输入输出缓存读取
Artificial Analysis · Gemini 4 Carbon (High)$4$20$0.2
Artificial Analysis · Gemini 4 Carbon (Low)$4$20$0.2
Artificial Analysis · Gemini 4 Carbon (Medium)$4$20$0.2

估算一次用量

按表格第一条报价计算,普通文本、无缓存。

预计费用$6
不含工具、图片、推理额外计费或阶梯价格;以服务商实际账单为准。

每个数字,都有出处

同名模型通过开发机构和明确版本关联。预览版、日期版本和不同规模模型分别建档。

Artificial Analysis

公开评测数据;保留来源原始口径

6 条记录最近采集 2026-11-10

LLM Stats

公开模型页与公开榜单;自报成绩单独标识

2 条记录最近采集 2026-11-10

BenchLM

公开评测数据;保留来源原始口径

1 条记录最近采集 2026-11-10

Arena

Arena 官方公开数据集 · CC BY 4.0

3 条记录最近采集 2026-11-10
查看全部配置与采集记录
来源 / 配置采集时间原始数据
Artificial AnalysisGemini 4 Carbon (high)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisGemini 4 Carbon (medium)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisGemini 4 Carbon (low)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisGemini 4 Carbon (High)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
Artificial AnalysisGemini 4 Carbon (Low)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
Artificial AnalysisGemini 4 Carbon (Medium)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
LLM StatsGemini 4 Carbon2026-11-10T14:08:28Z查看来源
LLM StatsGemini 4 CarbonSHA-256 518c0440e5096c0a…2026-11-10T13:51:54Z查看来源
BenchLMGemini 4 Carbon2026-11-10查看来源
ArenaGemini 4 Carbon (High)2026-11-10T14:07:52Z查看来源
ArenaGemini 4 Carbon (High)2026-11-10T14:07:52Z查看来源
ArenaGemini 4 Carbon (High)2026-11-10T14:07:52Z查看来源
继续浏览模型排行榜