openclaw 2026.11.1 · 单轮详情
20261107-openclaw-2026.11.1-t1
测量日 2026-11-07 · source SHA 4ffdd20
schema 缺测
provider: ppio；template: teams-work-v1；cpu: 4；memory_mib: 8192；os: Debian 13；deployment_kind: fresh_isolated
无独立交付快照；本页保留本轮公开指标。
| 版本 / 试次 | 测量日 | completed / 输入 | 内容 PASS | 回复耗时合计 / 秒 | 模型响应 | 工具调用 | 报告 |
|---|---|---|---|---|---|---|---|
| openclaw 2026.11.1 | 2026-11-07 | 14 / 14 | 9 / 10 | 767.6 | 125 | 120 | 详情与报告 |
逐用户输入
| 输入 | 原生终态 | 回复延迟 / 秒 | CLI / 观察耗时 / 秒 | 模型响应 | 工具调用 |
|---|---|---|---|---|---|
| C01/U1 | completed | 36.9 | 缺测 | 6 | 6 |
| C02/U1 | completed | 51.2 | 51.4 | 8 | 9 |
| C03/U1 | completed | 49.0 | 49.2 | 9 | 10 |
| C04/U1 | completed | 79.0 | 79.1 | 11 | 11 |
| C05/U1 | completed | 134.4 | 134.6 | 21 | 22 |
| C06/U1 | completed | 55.1 | 55.3 | 9 | 8 |
| C07/U1 | completed | 44.4 | 44.5 | 7 | 7 |
| C07/U2 | completed | 66.7 | 66.9 | 10 | 9 |
| C08/U1 | completed | 24.1 | 24.3 | 5 | 4 |
| C08/U2 | completed | 28.7 | 28.8 | 5 | 4 |
| C09/U1 | completed | 51.0 | 51.1 | 9 | 8 |
| C09/U2 | completed | 40.6 | 40.7 | 6 | 5 |
| C10/U1 | completed | 62.7 | 62.8 | 11 | 10 |
| C10/U2 | completed | 43.8 | 43.9 | 8 | 7 |
逐题内容判分
| 题目 | 内容复核 | 原检查器 | 回复合计 / 秒 |
|---|---|---|---|
| C01 发票去重与对账 | PASS | PASS | 36.9 |
| C02 日志关联与事故时间线 | PASS | PASS | 51.2 |
| C03 多文件政策优先级 | PASS | PASS | 49.0 |
| C04 时区与稳定排序 | PASS | PASS | 79.0 |
| C05 小模块修复与回归 | PASS | PASS | 134.4 |
| C06 依赖图与关键路径 | PASS | PASS | 55.1 |
| C07 采购方案追加预算约束 | PASS | PASS | 111.1 |
| C08 销售汇总与增量更正 | PASS | FAIL | 52.8 |
| C09 命令行工具连续迭代 | PASS | PASS | 91.6 |
| C10 发布判断与新证据修正 | INCONCLUSIVE | FAIL | 106.5 |
指标与缺测
{
"artifact_grades": {
"INCONCLUSIVE": 1,
"PASS": 9
},
"invocation_or_observer": {
"expected": 14,
"observed": 13,
"observed_sum_s": 732.6702414459999,
"sum_s": null
},
"model_id_mismatch": 0,
"model_id_missing": 0,
"native_tool_calls": 120,
"observed_model_ids": {
"deepseek/deepseek-v4.1-flash-1017": 125
},
"observed_model_intervals": {
"expected": 125,
"observed": 125,
"observed_sum_s": 732.121,
"sum_s": 732.121
},
"observed_tmp_commands": 5,
"observed_tool_intervals": {
"expected": 120,
"observed": 120,
"observed_sum_s": 14.22800064086914,
"sum_s": 14.22800064086914
},
"raw_artifact_grades": {
"FAIL": 2,
"PASS": 8
},
"response_latency": {
"expected": 14,
"observed": 14,
"observed_sum_s": 767.6273837089539,
"sum_s": 767.6273837089539
},
"scope_observed_cases": 10,
"terminals": {
"completed": 14
},
"tmp_command_cases": [
"C04",
"C09"
],
"tool_distribution": {
"edit": 8,
"exec": 74,
"ls": 7,
"read": 10,
"write": 21
},
"tool_input_availability": {
"unmarked": 120
},
"tool_missing_arguments": 0,
"tool_missing_results": 0,
"tool_output_availability": {
"unmarked": 120
},
"user_turns": 14,
"visible_model_responses": 125
}采集与覆盖说明（manifest 原文）
- All declared user turns have final reply timestamps
- Native model counts do not establish auxiliary/provider request completeness
- C01 CLI exit timing unavailable; native final reply available
口径与限制
n=1；并发争用、模型随机性、跨日基线未受控；不能据此作统计排名或因果结论。输入终态、内容判分、范围遵守与采集完整度分开呈现。
固定基线为2026-11-07 Codex0.165.0 / OpenClaw2026.11.1；欢喜OS各版本单独新增试次。相同10题、14用户输入，liqian deepseek/deepseek-v4.1-flash-1017。 每次报告明确区分：输入→原生终态延迟、CLI/观察收尾、模型响应、工具步骤、内容判分、范围遵守与证据缺测。跨日固定基线不是同时随机对照。
- Relative to historical .68/.69 (teams-work-v1), this run uses a different teams-work-v2 environment. Main comparison uses same-day .69 v2 environment anchor.
- Six versions execute concurrently in separate 4C/8G sandboxes; cross-version provider contention and model nondeterminism are uncontrolled. One trial per case; no statistical ranking or causal attribution.
内容复核口径（comparisons/latest.md）：历史复核：C08 原检查器漏查子目录备份，原判保留、内容复核 PASS；C10 部署清单完整性与 JSON 层级题面有歧义，保留 INCONCLUSIVE。
主耗时不包含CLI终态后退出等待。模型/工具时间线允许重叠；不得相加当整体墙钟。单trial及跨日历史基线只支持探索性比较。