Skip to main content

Model profile

GPT-5.6 Terra

OpenAICurrentReleased Jul 9, 2026
Data verified
Overall Score
72.57Public #11 of 200
Arena Elo
Not listed
Eligible category ranks
4of 8
Price (1M tokens)
$2.5 in / $15 out
API pricing
Speed
Not listed
Context
1M

Evidence coverage

45 of 323 tracked benchmarks are published. 24 are verified and 21 provisional. 7 of 8 categories are measured.

Updated July 23, 2026Methodology
Published / tracked
45 / 323
Verified
24
Provisional
21
Categories with evidence
7 / 8

Evidence by category

  • Agentic17 benchmarks
    Mixed evidence
  • Coding7 benchmarks
    Mixed evidence
  • Reasoning3 benchmarks
    Mixed evidence
  • Knowledge10 benchmarks
    Mixed evidence
  • Math3 benchmarks
    Verified
  • Multilingual0 benchmarks
    Not measured
  • Multimodal3 benchmarks
    Mixed evidence
  • Inst. Following1 benchmark
    Reported
ProprietaryReasoning
Confidence:
High
terra

GPT-5.6 Terra ranks #11 out of 200 models on the public leaderboard with an overall score of 72.57/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. This places it in the upper tier of AI models, with competitive scores across most benchmark categories.

GPT-5.6 Terra is a proprietary model with a 1M token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

GPT-5.6 Terra sits inside the GPT-5.6 family alongside GPT-5.6 Sol, GPT-5.6 Luna. This profile currently has 45 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Agentic (#2), while its weakest is Knowledge (#11). This performance profile makes it particularly useful for coding agents, browser research, and computer-use workflows.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 70.1974.24

  1. GPT-5.4
    OpenAI
    #874.24
    GPT-5.4 is #8 with a score of 74.24.
    Compare
  2. GPT-5.5
    OpenAI
    #973.51
    GPT-5.5 is #9 with a score of 73.51.
    Compare
  3. Qwen3.7 Max
    Alibaba
    #1072.84
    Qwen3.7 Max is #10 with a score of 72.84.
    Compare
  4. GPT-5.6 TerraCurrent model
    OpenAI
    #1172.57
    GPT-5.6 Terra is #11 with a score of 72.57.
  5. Claude Opus 4.7
    Anthropic
    #1271.94
    Claude Opus 4.7 is #12 with a score of 71.94.
    Compare
  6. Muse Spark
    Meta
    #1371.04
    Muse Spark is #13 with a score of 71.04.
    Compare
  7. MiMo-V2.5-Pro
    Xiaomi
    #1470.19
    MiMo-V2.5-Pro is #14 with a score of 70.19.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Agentic99%
    Eligible cohort rank #2 of 119Category score 73.1
  2. Multimodal75%
    Eligible cohort rank #8 of 29Category score 74.9
  3. Coding93%
    Eligible cohort rank #10 of 122Category score 66.0
  4. Knowledge80%
    Eligible cohort rank #11 of 52Category score 81.5

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #2 of 119Percentile 99thWeight 22%17 benchmarksMixed sources73.1
CodingRank #10 of 122Percentile 93rdWeight 20%7 benchmarksMixed sources66.0
ReasoningWeight 17%3 benchmarksMixed sourcesScore pending
KnowledgeRank #11 of 52Percentile 80thWeight 12%10 benchmarksMixed sources81.5
MathRank Not rankedWeight 5%3 benchmarksVerified97.1
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank #8 of 29Percentile 75thWeight 12%3 benchmarksMixed sources74.9
Inst. FollowingWeight 5%1 benchmarkReportedScore pending

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic17 benchmarks
Terminal-Bench 2.0Provider exact
87.4%Weighted 38%
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 87.4% on Terminal-Bench 2.1. BenchLM stores this on the existing Terminal-Bench 2 key.
BrowseCompProvider exact
87.5%Weighted 28%
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 87.5% on BrowseComp.
OSWorld 2.0Provider exact
50.2%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 50.2% on OSWorld 2.0.
CyberGymProvider exact
81.8%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 81.8% on CyberGym.
ExploitGymProvider exact
23.2%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 23.2% on ExploitGym.
ToolathlonProvider exact
53.1%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 53.1% on Toolathlon.
AA Agentic IndexReported

Artificial Analysis Agentic Index

47.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

86.3%Display only
Source: Artificial Analysis: tau2-bench leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
GDPval-AAReported

GDPval-AA normalized

54.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
GDPval-AAProvider exact
1581Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 1593 Elo on GDPval-AA v2.
AA Harvey LABReported

Artificial Analysis Harvey LAB-AA

85.2%Display only
Source: Artificial Analysis: harvey-lab-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA ITBenchReported

Artificial Analysis ITBench-AA

51.0%Display only
Source: Artificial Analysis: itbench-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA Tau3 BankingReported

Artificial Analysis Tau3-Banking

31.8%Display only
Source: Artificial Analysis: tau3-banking leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA AutomationBenchReported

Artificial Analysis AutomationBench

45.6%Display only
Source: Artificial Analysis: automationbench-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
terminalBenchHardReported
57.6%Display only
Source: Artificial Analysis: terminalbench-hard leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
aaTerminalBench21Reported
88%Display only
Source: Artificial Analysis: terminalbench-v2-1 leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
APEX-Agents-AAReported
38.9%Display only
Source: Artificial Analysis: apex-agents-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Coding7 benchmarks
SWE-bench ProProvider exact
63.4%Weighted 10%
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 63.4% on SWE-Bench Pro.
Terminal-Bench 2.0Provider exact
87.4%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 87.4% on Terminal-Bench 2.1. BenchLM stores this on the existing Terminal-Bench 2 key.
deepSweProvider exact
69.6%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 69.6% on DeepSWE v1.1. BenchLM stores DeepSWE as display-only because the source benchmark is an agent-harness coding signal.
FrontierCode 1.1 ExtendedProvider exact
55.8%Display only
Source: Cognition: GPT-5.6 models in DevinProvenance: Cognition reports GPT-5.6 Terra at 55.8% on the display-only FrontierCode 1.1 Extended subset in Devin.
cursorBench32Benchmark exact
64.9%Display only
Source: Cursor evals: CursorBench 3.2Provenance: Cursor reports GPT-5.6 Terra Max at this exact CursorBench 3.2 score on its public evals page. BenchLM stores it on the GPT-5.6 Terra row as a display-only coding-agent benchmark.
AA Coding IndexReported

Artificial Analysis Coding Index

76.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-SciCodeReported

Artificial Analysis SciCode

53.9%Display only
Source: Artificial Analysis: scicode leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Reasoning3 benchmarks
ARC-AGI-3Benchmark exact

Abstraction and Reasoning Corpus for AGI v3

0.8%Display only
Source: ARC Prize: GPT-5.6 verified resultsProvenance: ARC Prize reports GPT-5.6 Terra (Max) at 0.8% on ARC-AGI-3. This is distinct from ARC-AGI-2 and remains display-only.
AA-LCRReported

Artificial Analysis Long Context Reasoning

74.0%Display only
Source: Artificial Analysis: artificial-analysis-long-context-reasoning leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
CritPtSecondary exact

Critical Physics Tasks

30.0%Display only
Source: Artificial Analysis: CritPt Benchmark LeaderboardProvenance: Artificial Analysis reports GPT-5.6 Terra (max) at 30.0% on CritPt.
Knowledge10 benchmarks
GPQAProvider exact

Graduate-Level Google-Proof Q&A

92.9%Weighted 7%
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 92.9% on GPQA Diamond. BenchLM stores the value on both gpqa and gpqaDiamond for consistency with provider launch-table mappings.
GPQA-DProvider exact

GPQA Diamond

92.9%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 92.9% on GPQA Diamond.
HealthBench ProfessionalProvider exact
57.7%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 57.7% on HealthBench Professional using the official scoring approach from the HealthBench Professional paper.
HealthBench HardProvider exact
32.7%Display only
Source: OpenAI GPT-5.6 system cardProvenance: OpenAI's July 9, 2026 GPT-5.6 system card reports the length-adjusted HealthBench Hard score for GPT-5.6 Terra. BenchLM stores it as a display-only health benchmark row.
Artificial Analysis Intelligence IndexProvider exact
55.0%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 55.0 on Artificial Analysis Intelligence Index v4.1. BenchLM keeps this as a display-only Artificial Analysis row.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

92.5%Display only
Source: Artificial Analysis: gpqa-diamond leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

41.8%Display only
Source: Artificial Analysis: humanitys-last-exam leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

-0.2%Display only
Source: Artificial Analysis: omniscience leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

45.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

85.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Math3 benchmarks
FrontierMath v2 (Tiers 1-3)Provider exact

FrontierMath v2 Tiers 1-3

84.900%Weighted 30%
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 84.9% on FrontierMath v2 Tiers 1-3.
FrontierMath v2 (Tier 4)Provider exact

FrontierMath v2 Tier 4

68.300%Weighted 10%
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 68.3% on FrontierMath v2 Tier 4.
FrontierMath (legacy)Provider exact

FrontierMath legacy aggregate

84.9%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 84.9% on FrontierMath v2 Tier 1-3. BenchLM maps the existing FrontierMath field to this Tier 1-3 slice; the separate Tier 4 result is not combined.
Multimodal3 benchmarks
MMMU-ProProvider exact

Massive Multi-discipline Multimodal Understanding Pro

80.7%Weighted 45%
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 80.7% on MMMU Pro without tools.
MMMU-Pro w/ PythonProvider exact

MMMU-Pro with Python

82%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 82.0% on MMMU Pro with tools.
AA-MMMU-ProReported

Artificial Analysis MMMU-Pro

80.7%Display only
Source: Artificial Analysis: mmmu-pro leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

71.2%Display only
Source: Artificial Analysis: ifbench leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
External signals1 benchmark
ExploitBenchProvider exact

ExploitBench v8-bench

53%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Terra at 52.9% on ExploitBench. BenchLM stores this as a display-only external security row.

GPT-5.6 Family

terra · terra

Canonical Entry

GPT-5.6 Sol

Frequently Asked Questions

How does GPT-5.6 Terra perform overall in AI benchmarks?

GPT-5.6 Terra currently ranks #11 out of 200 models on BenchLM's provisional leaderboard with an overall score of 72.57. It is created by OpenAI. Its published context window is 1M.

Is GPT-5.6 Terra good for knowledge and understanding?

GPT-5.6 Terra ranks #11 out of 52 models in knowledge and understanding benchmarks with an average score of 81.5. There are stronger options in this category.

Is GPT-5.6 Terra good for coding and programming?

GPT-5.6 Terra ranks #10 out of 122 models in coding and programming benchmarks with an average score of 66. It is among the top performers in this category.

Is GPT-5.6 Terra good for mathematics?

GPT-5.6 Terra has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.

Is GPT-5.6 Terra good for reasoning and logic?

GPT-5.6 Terra has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is GPT-5.6 Terra good for agentic tool use and computer tasks?

GPT-5.6 Terra ranks #2 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 73.1. It is among the top performers in this category.

Is GPT-5.6 Terra good for multimodal and grounded tasks?

GPT-5.6 Terra ranks #8 out of 29 models in multimodal and grounded tasks benchmarks with an average score of 74.9. It is among the top performers in this category.

Is GPT-5.6 Terra good for instruction following?

GPT-5.6 Terra has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Which sibling models are related to GPT-5.6 Terra?

GPT-5.6 Terra belongs to the GPT-5.6 family. Related variants on BenchLM include GPT-5.6 Sol, GPT-5.6 Luna.

Does GPT-5.6 Terra have full benchmark coverage on BenchLM?

Not yet. GPT-5.6 Terra currently has 45 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of GPT-5.6 Terra?

GPT-5.6 Terra has a published context window of 1M, which determines how much text it can process in a single interaction.

Last updated: July 23, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.