Model profile
GPT-5.6 Terra
Evidence coverage
45 of 323 tracked benchmarks are published. 24 are verified and 21 provisional. 7 of 8 categories are measured.
- Published / tracked
- 45 / 323
- Verified
- 24
- Provisional
- 21
- Categories with evidence
- 7 / 8
Evidence by category
- Agentic17 benchmarksMixed evidence
- Coding7 benchmarksMixed evidence
- Reasoning3 benchmarksMixed evidence
- Knowledge10 benchmarksMixed evidence
- Math3 benchmarksVerified
- Multilingual0 benchmarksNot measured
- Multimodal3 benchmarksMixed evidence
- Inst. Following1 benchmarkReported
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 70.19–74.24
- GPT-5.4OpenAICompare#874.24GPT-5.4 is #8 with a score of 74.24.
- GPT-5.5OpenAICompare#973.51GPT-5.5 is #9 with a score of 73.51.
- Qwen3.7 MaxAlibabaCompare#1072.84Qwen3.7 Max is #10 with a score of 72.84.
- GPT-5.6 TerraCurrent modelOpenAI#1172.57GPT-5.6 Terra is #11 with a score of 72.57.
- Claude Opus 4.7AnthropicCompare#1271.94Claude Opus 4.7 is #12 with a score of 71.94.
- Muse SparkMetaCompare#1371.04Muse Spark is #13 with a score of 71.04.
- MiMo-V2.5-ProXiaomiCompare#1470.19MiMo-V2.5-Pro is #14 with a score of 70.19.
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.
- Agentic99%Eligible cohort rank #2 of 119Category score 73.1
- Multimodal75%Eligible cohort rank #8 of 29Category score 74.9
- Coding93%Eligible cohort rank #10 of 122Category score 66.0
- 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 | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #2 of 119Percentile 99thWeight 22%17 benchmarksMixed sources | 73.1 | #2 of 119 | 99th | 22% | 17 benchmarks | Mixed sources |
| CodingRank #10 of 122Percentile 93rdWeight 20%7 benchmarksMixed sources | 66.0 | #10 of 122 | 93rd | 20% | 7 benchmarks | Mixed sources |
| ReasoningWeight 17%3 benchmarksMixed sources | Score pending | Not ranked | Not available | 17% | 3 benchmarks | Mixed sources |
| KnowledgeRank #11 of 52Percentile 80thWeight 12%10 benchmarksMixed sources | 81.5 | #11 of 52 | 80th | 12% | 10 benchmarks | Mixed sources |
| MathRank Not rankedWeight 5%3 benchmarksVerified | 97.1 | Not ranked | Not available | 5% | 3 benchmarks | Verified |
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | Not ranked | Not available | 7% | 0 benchmarks | Not measured |
| MultimodalRank #8 of 29Percentile 75thWeight 12%3 benchmarksMixed sources | 74.9 | #8 of 29 | 75th | 12% | 3 benchmarks | Mixed sources |
| Inst. FollowingWeight 5%1 benchmarkReported | Score pending | Not ranked | Not available | 5% | 1 benchmark | Reported |
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
Artificial Analysis Agentic Index
τ²-Bench Tool-Agent-User Evaluation
GDPval-AA normalized
Artificial Analysis Harvey LAB-AA
Artificial Analysis ITBench-AA
Artificial Analysis Tau3-Banking
Artificial Analysis AutomationBench
Coding7 benchmarks
Artificial Analysis Coding Index
Artificial Analysis SciCode
Reasoning3 benchmarks
Abstraction and Reasoning Corpus for AGI v3
Artificial Analysis Long Context Reasoning
Critical Physics Tasks
Knowledge10 benchmarks
Graduate-Level Google-Proof Q&A
GPQA Diamond
Artificial Analysis GPQA Diamond
Artificial Analysis Humanity's Last Exam
Artificial Analysis Omniscience Index
Artificial Analysis Omniscience Accuracy
Artificial Analysis Omniscience Hallucination Rate
Math3 benchmarks
FrontierMath v2 Tiers 1-3
FrontierMath v2 Tier 4
FrontierMath legacy aggregate
Multimodal3 benchmarks
Massive Multi-discipline Multimodal Understanding Pro
MMMU-Pro with Python
Artificial Analysis MMMU-Pro
Inst. Following1 benchmark
Artificial Analysis IFBench
External signals1 benchmark
ExploitBench v8-bench
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.
Related Resources
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.