Home Model series GPT unsuffixed models GPT unsuffixed models · τ²-bench · Telecom section · Release history GPT unsuffixed models · τ²-bench · Telecom section · Release history View scores, configurations, and disclosures for τ²-bench · Telecom section across 5 GPT unsuffixed models releases, ordered by release date.
Differences are calculated only for unique, active, exact values between direct predecessors when the unit, metric, and explicitly recorded configuration and conditions match.
2025-08-07 · 1 score record for this release, including 1 exact value (may include historical records)
GPT-5 · τ²-bench scores and configurations Metric and score Configuration and evaluation conditions Sources Success rate 96.7% Reported 96.7% · Unit % Published 2025-08-07
GPT-5 (high) Settings API reasoning model; the developer release benchmark table labels high reasoning effort. Unknowns none recorded Tools Tools allowed Reasoning budget high Framework not recorded Protocol τ²-bench telecom Conditions API GPT-5; high reasoning effort. View this score in rankings
Detailed benchmarks / τ²-bench telecom Main text · Introducing GPT-5 for developers | OpenAI 2025-11-12 · 1 score record for this release, including 1 exact value (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
GPT-5.1 · τ²-bench scores and configurations Metric and score Configuration and evaluation conditions Sources Success rate 95.6% Reported 95.6% · Unit % Published 2025-11-13
GPT-5.1 (high) Settings Developer release table labels high reasoning effort; page separately describes adaptive reasoning in ChatGPT Instant/Thinking. Unknowns none recorded Tools Tool access not recorded Reasoning budget high Framework not recorded Protocol τ²-bench Telecom; a short, general-purpose prompt was added for GPT-5.1. Conditions High reasoning effort. View this score in rankings
2025-12-11 · 1 score record for this release, including 1 exact value (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
GPT-5.2 · τ²-bench scores and configurations Metric and score Configuration and evaluation conditions Sources Success rate 98.7% Reported 98.7% · Unit % Published Unconfirmed
GPT-5.2 Thinking (xhigh) Settings Highest available API reasoning effort xhigh, except professional benchmark tasks. Unknowns none recorded Tools Tools allowed Reasoning budget xhigh Framework not recorded Protocol τ²-bench Telecom; article notes a short, generally effective system prompt was added. Conditions Highest available API reasoning effort xhigh. View this score in rankings
2026-03-05 · 2 score records for this release, including 2 exact values (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
GPT-5.4 · τ²-bench scores and configurations Metric and score Configuration and evaluation conditions Sources Success rate 98.9% Reported 98.9% · Unit % Published Unconfirmed
GPT-5.4 (xhigh) Settings The release article states evaluations use xhigh unless otherwise noted. Unknowns none recorded Tools Tool access not recorded Reasoning budget xhigh Framework not recorded Protocol Tau2-bench Telecom;xhigh;未注明完整harness。 Conditions 当前官方页面;修订及具体披露日期未知。除明确 None 外,主表总体脚注为 xhigh;研究环境结果可能与上线产品略有差异。 View this score in rankings Success rate 64.3% Reported 64.3% · Unit % Published Unconfirmed
GPT-5.4 (none) Settings 官方“未开启推理的评估”表明确列名 GPT-5.4 (none)。 Unknowns 除表格与主文说明外,完整采样与评测脚手架未注明。 Tools Tool access not recorded Reasoning budget none Framework not recorded Protocol Tau2-bench Telecom;None;未注明完整harness。 Conditions 当前官方页面;修订及具体披露日期未知。除明确 None 外,主表总体脚注为 xhigh;研究环境结果可能与上线产品略有差异。 View this score in rankings
2026-04-23 · 5 score records for this release, including 5 exact values (may include historical records)
GPT-5.5 · τ²-bench scores and configurations Metric and score Configuration and evaluation conditions Sources Success rate 98% Reported 98.0% · Unit % Published Unconfirmed
GPT-5.5 xhigh Settings Reasoning effort xhigh; research environment; output may differ slightly from production ChatGPT in some cases. Unknowns A subset of protocol details remain benchmark-specific and unreported. Tools Tool access not recorded Reasoning budget xhigh Framework not recorded Protocol not specified Conditions Mainline GPT-5.5 evaluation at xhigh in research environment.; GPT-5.5; reasoning effort as labeled, otherwise xhigh per the article footnote; research environment. View this score in rankings Success rate 59.9% Reported 59.9% · Unit % Published Unconfirmed
GPT-5.5 none Settings Interactive chart labels reasoning effort none; chart-specific evaluation settings are otherwise not stated. Unknowns none recorded Tools Tool access not recorded Reasoning budget none Framework not recorded Protocol not specified Conditions GPT-5.5; reasoning effort as labeled, otherwise xhigh per the article footnote; research environment. View this score in rankings Success rate 82.2% Reported 82.2% · Unit % Published Unconfirmed
GPT-5.5 low Settings Interactive chart labels reasoning effort low; chart-specific evaluation settings are otherwise not stated. Unknowns none recorded Tools Tool access not recorded Reasoning budget low Framework not recorded Protocol not specified Conditions GPT-5.5; reasoning effort as labeled, otherwise xhigh per the article footnote; research environment. View this score in rankings Success rate 92.3% Reported 92.3% · Unit % Published Unconfirmed
GPT-5.5 medium Settings Interactive chart labels reasoning effort medium; chart-specific evaluation settings are otherwise not stated. Unknowns none recorded Tools Tool access not recorded Reasoning budget medium Framework not recorded Protocol not specified Conditions GPT-5.5; reasoning effort as labeled, otherwise xhigh per the article footnote; research environment. View this score in rankings Success rate 96.7% Reported 96.7% · Unit % Published Unconfirmed
GPT-5.5 high Settings Interactive chart labels reasoning effort high; chart-specific evaluation settings are otherwise not stated. Unknowns none recorded Tools Tool access not recorded Reasoning budget high Framework not recorded Protocol not specified Conditions GPT-5.5; reasoning effort as labeled, otherwise xhigh per the article footnote; research environment. View this score in rankings