Model reports

SlackBench

Agent 能否把聊天、代码和文档对照起来回答工作问题？比较成绩时，也要看它用什么工具读取资料。

原论文官方数据集收录来源

AI Benchmark Radar / Equality Machine · 核对于 2026-11-05

2026 年 11 月 3 日论文 v1，11 月 5 日核查。保留 33 个主配置、7 个 CLI 访问变体及 10 个推理变体，分类成绩与诊断分表展示。

核对协作空间

140 题覆盖搜索（58）、拒绝无依据作答（48）、总结（14）与情境推断（20）。重演环境包含 15 个频道、约 3,000 条消息、14 个仓库和 9 份文档。

SlackBench · original paper v1

四类任务等权

GPT-5.4 判定答案；总结按要点给部分分，结果取三次运行平均。虽然各类题数不同，整体仍按四类等权计算。

SlackBench · original paper v1

保留工具条件

主实验使用 medium 推理，每题限 20 分钟。CLI 访问与推理变体独立比较；运行日期和端点修订未明确。

SlackBench · original paper v1

理解证据范围

这是重演的学术工作流，部分参考答案不公开。人类基线允许 AI 辅助；裁判一致性只覆盖已抽查的输出。

SlackBench · original paper v1

全部主配置

保留原文数值。

全部主配置
框架	模型	搜索 %	拒答 %	总结 %	情境推断 %	整体 %
Antigravity	Gemini 4 Argon	70.69	90.28	76.68	83.33	80.25
Muse Code	Muse Wonder	81.03	62.50	71.42	80.00	73.74
Claude Code	Claude Fable 5.1	67.82	71.53	71.98	83.33	73.67
Claude Code	Claude Opus 5.5	71.84	75.00	70.42	73.33	72.65
Claude Code	Muse Wonder	68.97	66.67	67.25	80.00	70.72
Claude Code	GLM 5.3	69.54	70.83	65.12	58.33	65.96
Grok Build	Grok 4.7	64.94	56.94	70.01	70.00	65.47
Muse Code	Muse Spark 1.3	66.67	52.08	67.40	68.33	63.62
Codex CLI	GPT 6.1 Terra	63.22	55.56	64.05	61.67	61.12
Codex CLI	GPT 6 Astra	62.07	54.17	65.67	60.00	60.48
Codex CLI	GPT 6.1 Sol	59.77	50.69	62.30	60.00	58.19
Claude Code	Claude Opus 4.7	52.87	60.42	52.69	60.00	56.49
OpenHands	GPT-5.5	60.92	25.69	59.30	61.67	51.89
Terminus-2	GPT-5.5	56.32	21.53	48.72	66.67	48.31
Gemini CLI	Gemini 3.1 Pro Preview	54.02	42.36	38.74	50.00	46.28
Claude Code	Claude Sonnet 4.6	50.00	40.97	47.66	45.00	45.91
OpenHands	Claude Opus 4.6	48.28	15.28	53.24	66.67	45.87
Terminus-2	Claude Opus 4.6	54.60	11.81	56.71	60.00	45.78
Codex CLI	GPT-5.5	55.17	18.75	53.14	55.00	45.52
Claude Code	Kimi K2.6	50.00	32.64	49.11	46.67	44.60
Claude Code	Claude Opus 4.6	52.87	20.83	51.39	41.67	41.69
Terminus-2	Gemini 3.1 Pro Preview	50.00	34.72	27.35	50.00	40.52
Claude Code	DeepSeek V4 Pro	43.68	37.50	47.93	30.00	39.78
OpenHands	Gemini 3.1 Pro Preview	44.25	31.25	36.36	43.33	38.80
Terminus-2	Claude Sonnet 4.6	51.15	15.28	44.95	43.33	38.68
Claude Code	Qwen3.7 Max	36.78	38.19	41.23	36.67	38.22
Claude Code	GLM-5.1	50.00	22.22	50.09	30.00	38.08
Codex CLI	GPT-5.4	51.15	21.53	40.42	36.67	37.44
Codex CLI	GPT 6 Luna	45.98	22.92	44.05	36.67	37.40
Gemini CLI	Gemini 3 Flash Preview	42.53	1.39	27.26	53.33	31.13
Claude Code	Claude Haiku 4.5	38.51	26.39	30.15	15.00	27.51
Codex CLI	GPT-5.4-Mini	36.21	13.89	34.73	23.33	27.04
Terminus-2	GPT-5.4-Mini	22.41	5.56	16.63	6.67	12.82

medium 推理，SlackBench 模拟 MCP 接口。

SlackBench · main-results

资料访问方式对照

保留原文数值。

资料访问方式对照
框架	模型	访问方式	搜索 %	拒答 %	总结 %	情境推断 %	整体 %
Claude Code	Claude Opus 5.5	CLI	66.67	72.92	70.12	85.00	73.68
Claude Code	Claude Opus 5.5	MCP	71.84	75.00	70.42	73.33	72.65
Claude Code	Claude Opus 4.7	CLI	57.47	55.56	60.48	65.00	59.63
Claude Code	Claude Opus 4.7	MCP	52.87	60.42	52.69	60.00	56.49
Claude Code	Claude Sonnet 4.6	CLI	58.62	41.67	55.52	63.33	54.78
Claude Code	Claude Sonnet 4.6	MCP	50.00	40.97	47.66	45.00	45.91
Codex CLI	GPT-5.5	CLI	72.42	27.78	67.73	71.67	59.90
Codex CLI	GPT-5.5	MCP	55.17	18.75	53.14	55.00	45.52
Codex CLI	GPT-5.4-Mini	CLI	53.45	18.75	48.62	51.67	43.12
Codex CLI	GPT-5.4-Mini	MCP	36.21	13.89	34.73	23.33	27.04
Gemini CLI	Gemini 3.1 Pro Preview	CLI	62.07	37.50	51.01	66.67	54.31
Gemini CLI	Gemini 3.1 Pro Preview	MCP	54.02	42.36	38.74	50.00	46.28
Gemini CLI	Gemini 3 Flash Preview	CLI	42.53	3.47	33.86	58.33	34.55
Gemini CLI	Gemini 3 Flash Preview	MCP	42.53	1.39	27.26	53.33	31.13

MCP 行重复对应主基线，不重复增加成绩记录。

SlackBench · access-results

推理强度对照

保留原文数值。

推理强度对照
框架	模型	推理	搜索 %	拒答 %	总结 %	情境推断 %	整体 %
Claude Code	Claude Opus 4.7	Low	50.00	50.00	45.19	50.00	48.80
Claude Code	Claude Opus 4.7	Medium	52.87	60.42	52.69	60.00	56.49
Claude Code	Claude Opus 4.7	High	58.62	72.92	63.94	75.00	67.62
Claude Code	Claude Sonnet 4.6	Low	39.66	41.67	40.86	55.00	44.30
Claude Code	Claude Sonnet 4.6	Medium	50.00	40.97	47.66	45.00	45.91
Claude Code	Claude Sonnet 4.6	High	55.17	33.33	44.96	60.00	48.37
Codex CLI	GPT-5.5	Low	48.28	18.75	51.52	45.00	40.89
Codex CLI	GPT-5.5	Medium	55.17	18.75	53.14	55.00	45.52
Codex CLI	GPT-5.5	High	58.62	25.00	60.90	65.00	52.38
Codex CLI	GPT-5.4-mini	Low	25.86	10.41	24.80	0.00	15.27
Codex CLI	GPT-5.4-mini	Medium	36.21	13.89	34.73	23.33	27.04
Codex CLI	GPT-5.4-mini	High	41.38	10.42	38.09	20.00	27.47
Gemini CLI	Gemini 3.1 Pro Preview	Low	43.10	37.50	27.04	45.00	38.16
Gemini CLI	Gemini 3.1 Pro Preview	Medium	54.02	42.36	38.74	50.00	46.28
Gemini CLI	Gemini 3.1 Pro Preview	High	58.62	37.50	39.83	55.00	47.74

medium 行重复主基线。

SlackBench · effort-results

筛选题的官方接口对照

保留原文数值。

筛选题的官方接口对照
框架	模型	接口	筛选搜索 %	筛选拒答 %
Claude Code	Claude Opus 4.7	Ours	53.33	53.19
Claude Code	Claude Opus 4.7	Official MCP	57.78	59.57
Claude Code	Claude Sonnet 4.6	Ours	46.67	34.04
Claude Code	Claude Sonnet 4.6	Official MCP	57.78	38.30
Codex CLI	GPT-5.5	Ours	53.33	18.09
Codex CLI	GPT-5.5	Official MCP	55.56	25.53
Codex CLI	GPT-5.4-Mini	Ours	46.67	12.77
Codex CLI	GPT-5.4-Mini	Official MCP	46.67	19.15

仅筛选后的 AS/HA 题，不是完整评测总分。

SlackBench · official-tools

裁判间一致率

保留原文数值。

裁判间一致率
裁判	GPT-5.4 %	Opus 4.7 %	Gemini 3.1 Pro %
GPT-5.4	100%	95.1%	96.3%
Opus 4.7	–	100%	96.6%
Gemini 3.1 Pro	–	–	100%

来自六个指定 Agent 配置的 AS、HA、CI 答案；不是任务正确率。

SlackBench · judge-agreement

允许 AI 辅助的人类基线

三名独立研究者的均值与区间。

人类参考
整体 %	搜索 %	拒答 %	总结 %	情境推断 %	95% bootstrap 区间
84.5	91	90	82	75	77.0–92.0

允许 AI 辅助，不代表不使用 AI 的人类表现。

SlackBench · human

原始发布

2026 年 11 月 3 日论文 v1，11 月 5 日核查。保留 33 个主配置、7 个 CLI 访问变体及 10 个推理变体，分类成绩与诊断分表展示。

核对于 2026-11-05

已收录的评测资料

这条来源记录收录了 50 条数值成绩。来源区分了 24 个模型身份或配置。同一模型可能有多条记录；比较前请核对具体版本、工具和运行预算。查看成绩及逐条证据 →

报告指标: overall accuracy (unweighted mean of four category scores)
原始单位: percent
指标方向: 数值越高越好

从这些资料开始

收录来源 · arxiv.org

引用文档及日期（1）

SlackBench · original v1 evaluation · 2026-11-03

评测信息与证据

来源: Model reports
发布者: 未收录
评测发布日期: 2026-11-03
采集日期: 未收录
模态: 未收录

本站保留来源报告的结果，不代表独立复测。请先核对任务版本、评测协议、分数单位和报告日期；不同运行条件不能直接合并为统一排名。

报告成绩 50

按来源中的观察顺序展示，顺序不代表排名。日期保留原始精度。

模型	数值	单位	协议	报告日期与口径	来源
Gemini 4 Argon	80.25	percent	Antigravity harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Opus 4.7	67.62	percent	Claude Code harness; SlackBench mock MCP workspace access; high reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Sonnet 4.6	48.37	percent	Claude Code harness; SlackBench mock MCP workspace access; high reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Opus 4.7	48.8	percent	Claude Code harness; SlackBench mock MCP workspace access; low reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Sonnet 4.6	44.3	percent	Claude Code harness; SlackBench mock MCP workspace access; low reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Fable 5.1	73.67	percent	Claude Code harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Haiku 4.5	27.51	percent	Claude Code harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Opus 4.6	41.69	percent	Claude Code harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Opus 4.7	56.49	percent	Claude Code harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Opus 5.5	72.65	percent	Claude Code harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Sonnet 4.6	45.91	percent	Claude Code harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
DeepSeek V4 Pro	39.78	percent	Claude Code harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GLM 5.3	65.96	percent	Claude Code harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GLM-5.1	38.08	percent	Claude Code harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Kimi K2.6	44.6	percent	Claude Code harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Muse Wonder	70.72	percent	Claude Code harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Qwen3.7 Max	38.22	percent	Claude Code harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Opus 4.7	59.63	percent	Claude Code harness; direct terminal access to exported Slack workspace; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Opus 5.5	73.68	percent	Claude Code harness; direct terminal access to exported Slack workspace; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Sonnet 4.6	54.78	percent	Claude Code harness; direct terminal access to exported Slack workspace; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT-5.4-Mini	27.47	percent	Codex CLI harness; SlackBench mock MCP workspace access; high reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT-5.5	52.38	percent	Codex CLI harness; SlackBench mock MCP workspace access; high reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT-5.4-Mini	15.27	percent	Codex CLI harness; SlackBench mock MCP workspace access; low reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT-5.5	40.89	percent	Codex CLI harness; SlackBench mock MCP workspace access; low reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT 6 Astra	60.48	percent	Codex CLI harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT 6 Luna	37.4	percent	Codex CLI harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT 6.1 Sol	58.19	percent	Codex CLI harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT 6.1 Terra	61.12	percent	Codex CLI harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT-5.4	37.44	percent	Codex CLI harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT-5.4-Mini	27.04	percent	Codex CLI harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT-5.5	45.52	percent	Codex CLI harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT-5.4-Mini	43.12	percent	Codex CLI harness; direct terminal access to exported Slack workspace; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT-5.5	59.9	percent	Codex CLI harness; direct terminal access to exported Slack workspace; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Gemini 3.1 Pro Preview	47.74	percent	Gemini CLI harness; SlackBench mock MCP workspace access; high reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Gemini 3.1 Pro Preview	38.16	percent	Gemini CLI harness; SlackBench mock MCP workspace access; low reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Gemini 3 Flash Preview	31.13	percent	Gemini CLI harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Gemini 3.1 Pro Preview	46.28	percent	Gemini CLI harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Gemini 3 Flash Preview	34.55	percent	Gemini CLI harness; direct terminal access to exported Slack workspace; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Gemini 3.1 Pro Preview	54.31	percent	Gemini CLI harness; direct terminal access to exported Slack workspace; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Grok 4.7	65.47	percent	Grok Build harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Muse Spark 1.3	63.62	percent	Muse Code harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Muse Wonder	73.74	percent	Muse Code harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Opus 4.6	45.87	percent	OpenHands harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT-5.5	51.89	percent	OpenHands harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Gemini 3.1 Pro Preview	38.8	percent	OpenHands harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Opus 4.6	45.78	percent	Terminus-2 harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Claude Sonnet 4.6	38.68	percent	Terminus-2 harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT-5.4-Mini	12.82	percent	Terminus-2 harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
GPT-5.5	48.31	percent	Terminus-2 harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation
Gemini 3.1 Pro Preview	40.52	percent	Terminus-2 harness; SlackBench mock MCP workspace access; medium reasoning; Harbor, 20-minute query limit; average of three runs and equal mean of AS/HA/SU/CI; GPT-5.4 judge, SU partial checklist credit; read-only Slack/GitHub tools plus terminal and web search; original publication date, exact run dates/API revisions unknown	2026-11-03 · document_publication	SlackBench · original v1 evaluation

核对协作空间

四类任务等权

保留工具条件

理解证据范围

全部主配置

资料访问方式对照

推理强度对照

筛选题的官方接口对照

裁判间一致率

允许 AI 辅助的人类基线

原始发布

已收录的评测资料

从这些资料开始

评测信息与证据

报告成绩 50

相关评测探索

继续阅读

继续探索