拾穗数据工作室SQL 模型评测台

失败 · 2026年8月30日 00:20

运行 #8 评测报告

Sol,1 道题。综合得分为规则加权分,不是正确率。

比较条件存在差异:single_model。阅读模型间差距时必须保留这一前提。

逐题结果原始报告 JSON ↗事件 JSONL ↗
gpt-5.6-sol

Sol

综合得分 / 100
0.00
1题目数量
1每题尝试次数
1失败案例

样本边界:结论仅适用于此题库哈希、模型版本、适配器和参数快照。跨版本、跨运行稳定性需要独立复测。

得分与资源消耗

新 efficiency-v2 按业务结果正确题数归一;旧 efficiency-v1 保留综合得分 ÷ 100 的折算口径,两种指标不能混排。记录不完整时不估算单位正确题消耗。

指标Sol
综合得分
固定规则加权 / 100
0.00
Token / 归一单位每得分折算题 · 未记录
费用 / 归一单位
基于冻结价格;缺失不估
不可估算每得分折算题 · unavailable
生成耗时中位数
模型生成阶段
P95 —

分项得分

分项为加权得分,不是业务结果正确率。

题目维度Sol
基础查询0.00

逐题结果

得分为全部计划尝试的均分,失败计入分母,未完成显示未知。展开可查看每次作答。

基础筛选与排序basic_filter_sort0.00

Sol

全部 1 次计划作答 · 结果正确性未知

A1 · 失败 · 0.00

Codex 退出码 1: 2026-08-29T16:21:04.268707Z ERROR codex_models_manager::manager: failed to refresh available models: timeout waiting for child process to exit 2026-08-29T16:21:04.289121Z ERROR codex_models_manager::manager: failed to refresh available models: timeout waiting for child process to exit 2026-08-29T16:21:04.880033Z ERROR rmcp::transport::worker: worker quit with fatal: Transport channel closed, when Client(HttpRequest(HttpRequest("http/request failed: error sending request for url (https://chatgpt.com/backend-api/ps/mcp)"))) 2026-08-29T16:21:05.559988Z ERROR rmcp::transport::worker: worker quit with fatal: Transport channel closed, when Client(HttpRequest(HttpRequest("http/request failed: error sending request for url (https://chatgpt.com/backend-api/ps/mcp)"))) 2026-08-29T16:21:07.052524Z ERROR rmcp::transport::worker: worker quit with fatal: Transport channel closed, when Client(HttpRequest(HttpRequest("http/request failed: error sending request for url (https://chatgpt.com/backend-api/ps/mcp)"))) 2026-08-29T16:21:07.540537Z ERROR rmcp::transport::worker: worker quit with fatal: Transport channel closed, when Client(HttpRequest(HttpRequest("http/request failed: error sending request for url (https://chatgpt.com/backend-api/ps/mcp)"))) 2026-08-29T16:21:07.545337Z ERROR codex_api::endpoint::responses_websocket: failed to connect to websocket: IO error: invalid peer certificate: UnknownIssuer, url: wss://chatgpt.com/backend-api/codex/responses 2026-08-29T16:21:08.461404Z ERROR rmcp::transport::worker: worker quit with fatal: Transport channel closed, when Client(HttpRequest(HttpRequest("http/request failed: error sending request for url (https://chatgpt.com/backend-api/ps/mcp)"))) 2026-08-29T16:21:09.507114Z ERROR codex_api::endpoint::responses_websocket: failed to connect to websocket: IO error: invalid peer certificate: UnknownIssuer, url: wss://chatgpt.com/backend-api/codex/responses 2026-08-29T16:21:09.972761Z ERROR rmcp::transport::worker: worker quit with fatal: Transport channel closed, when Client(HttpRequest(HttpRequest("http/request failed: error sending request for url (https://chatgpt.com/backend-api/ps/mcp)"))) 2026-08-29T16:21:10.140317Z ERROR codex_api::endpoint::responses_websocket: failed to connect to websocket: IO error: invalid peer certificate: UnknownIssuer, url: wss://chatgpt.com/backend-api/codex/responses 2026-08-29T16:21:11.037311Z ERROR codex_api::endpoint::responses_websocket: failed to connect to websocket: IO error: invalid peer certificate: UnknownIssuer, url: wss://chatgpt.com/backend-api/codex/responses 2026-08-29T16:21:12.322380Z ERROR codex_api::endpoint::responses_websocket: failed to connect to websocket: IO error: invalid peer certificate: UnknownIssuer, url: wss://chatgpt.com/backend-api/codex/responses 2026-08-29T16:21:14.449644Z ERROR codex_api::endpoint::responses_websocket: failed to connect to websocket: IO error: invalid peer certificate: UnknownIssuer, url: wss://chatgpt.com/backend-api/codex/responses 2026-08-29T16:21:17.896684Z ERROR codex_api::endpoint::responses_websocket: failed to connect to websocket: IO error: invalid peer certificate: UnknownIssuer, url: wss://chatgpt.com/backend-api/codex/responses

结果正确性未知

查看 A1 完整证据