Updated November 6, 2026. Rank says GPT-5.6 Terra is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
GPT-5.6 Terra has the higher public score estimate, 69.81 versus 62.59, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 12 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Code generation, repair, and software-engineering tasks
GPT-5.6 Terra
GPT-5.6 Terra has the higher public coding point estimate, 62.1 to 51.8, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
1K fresh input + 500 output tokens
GPT-6 Luna
GPT-6 Luna has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
GPT-6 Luna
GPT-6 Luna has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
GPT-6 Luna
GPT-6 Luna has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Tool use, computer use, and multi-step task completion
Not enough matched evidence
GPT-6 Luna is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
Like-for-like · BenchAlign v5.8
GPT-5.6 Terra has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
ARC-AGI-2Reasoning
Normalized gap 24.6FrontierMath v2 (Tier 4)Math
Normalized gap 12.2FrontierMath v2 (Tiers 1-3)Math
Normalized gap 6.0ARC-AGI-3Reasoning
Normalized gap 0.7Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
| Category | GPT-5.6 Terra | GPT-6 Luna | Basis | Reading |
|---|---|---|---|---|
| Coding | 62.1Supported · #16/157 | 51.8Supported · #42/157 | Like-for-likeBenchAlign v5.8 lane · 9 vs 3 public rows | GPT-5.6 Terra leads · intervals overlap |
| Reasoning | 67.4#16/25 | 57.5#22/25 | Like-for-likeProvisional lane · 2 vs 2 weighted rows | GPT-5.6 Terra leads |
| Knowledge | 69.3Supported · #18/178 | 63.3Supported · #40/178 | Like-for-likeBenchAlign v5.8 lane · 8 vs 5 public rows | GPT-5.6 Terra leads · intervals overlap |
| Agentic | 60.3Supported · #25/131 | 53.5Estimated · #45/131 | Directional onlyBenchAlign v5.8 lane · 10 vs 5 public rows | Directional only |
| Multimodal | 84.2#15/59 | 81.9Unranked · 1 rankable row | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | 87.1#42/157 | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 86.6Unranked · 3 rankable rows | 80.2Unranked · 2 rankable rows | Not comparableProvisional lane · 2 vs 2 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
1K fresh input + 500 output tokens
GPT-6 Luna has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
GPT-6 Luna has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
GPT-6 Luna has the lower modeled cost
Costs use the listed standard API rates.
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
GPT-5.6 Terra
1.05M
OpenAI model catalogGPT-6 Luna
GPT-5.6 Terra
gpt-5.6-terra
OpenAI model catalogGPT-6 Luna
gpt-6-luna
OpenAI GPT-6 Luna model documentationA missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GPT-5.6 Terra
$0.2 per 1M cached input tokens
OpenAI pricingGPT-6 Luna
$0.01 per 1M cached input tokens
OpenAI GPT-6 Luna model documentationGPT-5.6 Terra
text, image
OpenAI model catalogGPT-6 Luna
text, image
OpenAI GPT-6 Luna model documentationGPT-5.6 Terra
GPT-6 Luna
GPT-5.6 Terra
Generally Available · OpenAI Responses API
OpenAI model catalogGPT-6 Luna
Generally Available · OpenAI Responses API, OpenAI Chat Completions API, ChatGPT Work, Codex
OpenAI GPT-6 Sol and Luna launchGPT-5.6 Terra
Reasoning
GPT-6 Luna
Reasoning
GPT-5.6 Terra
Proprietary
GPT-6 Luna
Proprietary
GPT-5.6 Terra
Proprietary
GPT-6 Luna
Proprietary
GPT-5.6 Terra
2026-07-09
GPT-6 Luna
2026-09-22
GPT-5.6 Terra has the higher public score estimate, 69.81 versus 62.59, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
GPT-5.6 Terra has the higher public coding point estimate, 62.1 to 51.8, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
GPT-5.6 Terra scores higher for agentic tasks on the public lane, 60.3 to 53.5. GPT-6 Luna is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
For the stated presets, chat costs $0.008 on GPT-5.6 Terra and $0.00035 on GPT-6 Luna; repository review costs $0.136 and $0.0065; the cache-heavy agent loop costs $0.2 and $0.009. Costs use the listed standard API rates.
Both models list the same context window, 1.05M.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 3.0
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
BrowseComp
Not directly comparable
OSWorld 2.0
Not directly comparable
CyberGym
Not directly comparable
ExploitGym
GPT-5.6 Terra leads this result
Toolathlon
Not directly comparable
Terminal-Bench 2.1 (Vals)
Not directly comparable
ApprenticeBench
Not directly comparable
MazeBench
GPT-5.6 Terra leads this result
Hermes Index
Not directly comparable
Hermes Bench
Not directly comparable
OSWorld 2.1 Offline
Not directly comparable
SWE-bench Pro
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
DeepSWE
GPT-5.6 Terra leads this result
FrontierCode 1.1 Extended
Not directly comparable
CursorBench 3.2
Not directly comparable
VulcanBench v3
Not directly comparable
LiveCodeBench (Vals)
Not directly comparable
SWE-bench (Vals)
Not directly comparable
CursorBench 4.0
Not directly comparable
Bug Hunt Bench
Not directly comparable
FrontierCode 2.0
Not directly comparable
ARC-AGI-2
GPT-5.6 Terra leads this result
ARC-AGI-3
GPT-5.6 Terra leads this result
ARC-AGI-1
GPT-5.6 Terra leads this result
BioBasicsBench
Not directly comparable
ARC-AGI-3 Provider Adapter
Not directly comparable
ExtractBench (LlamaIndex)
Shared sourceGPT-5.6 Terra leads this result
ParseBench
Shared sourceGPT-5.6 Terra leads this result
MMMU-Pro
Not directly comparable
MMMU-Pro w/ Python
Not directly comparable
ExtractBench Pro
Not directly comparable
GPQA
Not directly comparable
GPQA-D
Not directly comparable
HLE-Verified
Not directly comparable
LABBench2
Not directly comparable
HealthBench Professional
GPT-6 Luna leads this result
HealthBench Hard
GPT-5.6 Terra leads this result
GPQA Diamond (Vals)
Not directly comparable
MMLU-Pro (Vals)
Not directly comparable
HealthBench (raw)
Not directly comparable
HealthBench (length-adjusted)
Not directly comparable
HealthBench Professional (raw)
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 6,100+ subscribers.
Last updated November 6, 2026
