Home Model series GPT Terra GPT Terra · MMMU-Pro · Vision format explicitly labeled by the official comparison chart; task release/version unspecified · Release history GPT Terra · MMMU-Pro · Vision format explicitly labeled by the official comparison chart; task release/version unspecified · Release history View scores, configurations, and disclosures for MMMU-Pro · Vision format explicitly labeled by the official comparison chart; task release/version unspecified across 2 GPT Terra 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.
2026-07-09 · 5 score records for this release, including 5 exact values (may include historical records)
GPT-5.6 Terra · MMMU-Pro scores and configurations Metric and score Configuration and evaluation conditions Sources Score 74.9% Reported 74.9% · Unit % Published 2026-10-26
GPT-5.6 Terra low Settings GPT-5.6 Terra; reasoning effort low, directly labeled in the official chart. Unknowns Sampling and harness settings are not stated for this chart. Tools Tool access not recorded Reasoning budget low Framework not recorded Protocol MMMU-Pro (Vision); y metric Score; x axis Cost (USD). Conditions GPT-5.6 Terra; reasoning effort Low; chart cost $0.011. View this score in rankings Score 76.4% Reported 76.4% · Unit % Published 2026-10-26
GPT-5.6 Terra medium Settings GPT-5.6 Terra; reasoning effort medium, directly labeled in the official chart. Unknowns Sampling and harness settings are not stated for this chart. Tools Tool access not recorded Reasoning budget medium Framework not recorded Protocol MMMU-Pro (Vision); y metric Score; x axis Cost (USD). Conditions GPT-5.6 Terra; reasoning effort Medium; chart cost $0.012. View this score in rankings Score 77.5% Reported 77.5% · Unit % Published 2026-10-26
GPT-5.6 Terra high Settings GPT-5.6 Terra; reasoning effort high, directly labeled in the official chart. Unknowns Sampling and harness settings are not stated for this chart. Tools Tool access not recorded Reasoning budget high Framework not recorded Protocol MMMU-Pro (Vision); y metric Score; x axis Cost (USD). Conditions GPT-5.6 Terra; reasoning effort High; chart cost $0.014. View this score in rankings Score 78.7% Reported 78.7% · Unit % Published 2026-10-26
GPT-5.6 Terra xhigh Settings GPT-5.6 Terra; reasoning effort xhigh, directly labeled in the official chart. Unknowns Sampling and harness settings are not stated for this chart. Tools Tool access not recorded Reasoning budget xhigh Framework not recorded Protocol MMMU-Pro (Vision); y metric Score; x axis Cost (USD). Conditions GPT-5.6 Terra; reasoning effort Xhigh; chart cost $0.02. View this score in rankings Score 81.7% Reported 81.7% · Unit % Published 2026-10-26
GPT-5.6 Terra max Settings GPT-5.6 Terra; reasoning effort max, directly labeled in the official chart. Unknowns Sampling and harness settings are not stated for this chart. Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol MMMU-Pro (Vision); y metric Score; x axis Cost (USD). Conditions GPT-5.6 Terra; reasoning effort Max; chart cost $0.079. View this score in rankings
2026-10-26 · 5 score records for this release, including 5 exact values (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
GPT-6.1 Terra · MMMU-Pro scores and configurations Metric and score Configuration and evaluation conditions Sources Score 83.7% Reported 83.7% · Unit % Published Unconfirmed
GPT-6.1 Terra low Settings GPT-6.1 Terra; reasoning effort low, directly labeled in the official chart. Unknowns Sampling and harness settings are not stated for this chart. Tools Tool access not recorded Reasoning budget low Framework not recorded Protocol MMMU-Pro (Vision); y metric Score; x axis Cost (USD). Conditions GPT-6.1 Terra; reasoning effort Low; chart cost $0.0038. View this score in rankings Score 84.6% Reported 84.6% · Unit % Published Unconfirmed
GPT-6.1 Terra medium Settings GPT-6.1 Terra; reasoning effort medium, directly labeled in the official chart. Unknowns Sampling and harness settings are not stated for this chart. Tools Tool access not recorded Reasoning budget medium Framework not recorded Protocol MMMU-Pro (Vision); y metric Score; x axis Cost (USD). Conditions GPT-6.1 Terra; reasoning effort Medium; chart cost $0.0041. View this score in rankings Score 85% Reported 85.0% · Unit % Published Unconfirmed
GPT-6.1 Terra high Settings GPT-6.1 Terra; reasoning effort high, directly labeled in the official chart. Unknowns Sampling and harness settings are not stated for this chart. Tools Tool access not recorded Reasoning budget high Framework not recorded Protocol MMMU-Pro (Vision); y metric Score; x axis Cost (USD). Conditions GPT-6.1 Terra; reasoning effort High; chart cost $0.0045. View this score in rankings Score 85.4% Reported 85.4% · Unit % Published Unconfirmed
GPT-6.1 Terra xhigh Settings GPT-6.1 Terra; reasoning effort xhigh, directly labeled in the official chart. Unknowns Sampling and harness settings are not stated for this chart. Tools Tool access not recorded Reasoning budget xhigh Framework not recorded Protocol MMMU-Pro (Vision); y metric Score; x axis Cost (USD). Conditions GPT-6.1 Terra; reasoning effort Xhigh; chart cost $0.0055. View this score in rankings Score 85.5% Reported 85.5% · Unit % Published Unconfirmed
GPT-6.1 Terra max Settings GPT-6.1 Terra at maximum reasoning effort, as stated in the release article for Terminal-Bench 4.0. Unknowns Other sampling and harness settings are not disclosed in the release article. Tools Tool access not recorded Reasoning budget maximum Framework not recorded Protocol MMMU-Pro (Vision); y metric Score; x axis Cost (USD). Conditions GPT-6.1 Terra; reasoning effort Max; chart cost $0.012. View this score in rankings