Updated November 10, 2026. Rank says GPT-5.6 Luna is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
GPT-5.6 Luna has the higher public score, 63.72 versus 46.51, and the 90% score intervals do not overlap. 14 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
GPT-5.4 nano: $0.20 input / $1.25 output
GPT-5.6 Luna: $0.20 input / $1.20 output
GPT-5.4 nano: 400K
GPT-5.6 Luna: 1.05M
GPT-5.4 nano: March 17, 2026
GPT-5.6 Luna: July 9, 2026
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 Luna
GPT-5.6 Luna has the higher public coding point estimate, 61.9 to 30.2, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Tool use, computer use, and multi-step task completion
GPT-5.6 Luna
GPT-5.6 Luna has the higher public agentic point estimate, 59.1 to 33.3, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Prompts that approach the documented context limit
GPT-5.6 Luna
GPT-5.6 Luna has the larger documented context window.
1K fresh input + 500 output tokens
GPT-5.6 Luna
GPT-5.6 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-5.6 Luna
GPT-5.6 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-5.6 Luna
GPT-5.6 Luna has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
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 Luna 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.
The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
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 53.8FrontierMath v2 (Tier 4)Math
Normalized gap 46.3FrontierMath v2 (Tiers 1-3)Math
Normalized gap 33.7MMMU-ProMultimodal
Normalized gap 12.3GPQAKnowledge
Normalized gap 9.5Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, reasoning, multimodal, 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-5.4 nano | GPT-5.6 Luna | Basis | Reading |
|---|---|---|---|---|
| Agentic | 33.3Supported · #96/132 | 59.1Supported · #33/132 | Like-for-likeBenchAlign v5.8 lane · 6 vs 11 public rows | GPT-5.6 Luna leads |
| Coding | 30.2Supported · #108/158 | 61.9Supported · #17/158 | Like-for-likeBenchAlign v5.8 lane · 4 vs 8 public rows | GPT-5.6 Luna leads |
| Reasoning | 37.6Supported · #95/158 | 58.3Supported · #36/158 | Like-for-likeBenchAlign v5.8 lane · 2 vs 3 public rows | GPT-5.6 Luna leads |
| Multimodal | 38.8Supported · #63/67 | 65.4Supported · #23/67 | Like-for-likeBenchAlign v5.8 lane · 4 vs 4 public rows | GPT-5.6 Luna leads |
| Knowledge | 38.9Supported · #120/179 | 63.1Supported · #40/179 | Like-for-likeBenchAlign v5.8 lane · 5 vs 6 public rows | GPT-5.6 Luna leads |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | 93.3#12/157 | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 48.3Unranked · 2 rankable rows | 78.9Unranked · 3 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, reasoning, multimodal, 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-5.6 Luna has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
GPT-5.6 Luna has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
GPT-5.6 Luna has the lower modeled cost
Costs use the listed standard API rates.
Enter a month of tokens to price it at both models’ listed API rates.
Standard listed rates, no batch or volume discounts.
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-5.4 nano
GPT-5.6 Luna
1.05M
OpenAI model catalogGPT-5.4 nano
gpt-5.4-nano
OpenAI GPT-5.4 nano model documentationGPT-5.6 Luna
gpt-5.6-luna
OpenAI model catalogA missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GPT-5.4 nano
$0.02 per 1M cached input tokens
OpenAI pricingGPT-5.6 Luna
$0.02 per 1M cached input tokens
OpenAI pricingGPT-5.4 nano
text, image
OpenAI model catalogGPT-5.6 Luna
text, image
OpenAI model catalogGPT-5.4 nano
GPT-5.6 Luna
GPT-5.4 nano
Generally Available · OpenAI Responses API
OpenAI model catalogGPT-5.6 Luna
Generally Available · OpenAI Responses API
OpenAI model catalogGPT-5.4 nano
Reasoning
GPT-5.6 Luna
Reasoning
GPT-5.4 nano
Proprietary
GPT-5.6 Luna
Proprietary
GPT-5.4 nano
Proprietary
GPT-5.6 Luna
Proprietary
GPT-5.4 nano
2026-03-17
GPT-5.6 Luna
2026-07-09
GPT-5.6 Luna has the higher public score, 63.72 versus 46.51, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
GPT-5.6 Luna has the higher public coding point estimate, 61.9 to 30.2, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
GPT-5.6 Luna has the higher public agentic tasks point estimate, 59.1 to 33.3, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
For the stated presets, chat costs $0.00082 on GPT-5.4 nano and $0.0008 on GPT-5.6 Luna; repository review costs $0.01375 and $0.0136; the cache-heavy agent loop costs $0.0205 and $0.02. Costs use the listed standard API rates.
GPT-5.6 Luna has the larger documented context window: 1.05M, compared with 400K.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 2.0
Not directly comparable
OSWorld-Verified
Not directly comparable
MCP Atlas
Not directly comparable
Toolathlon
GPT-5.6 Luna leads this result
τ²-bench results
Not directly comparable
Terminal-Bench 2.1 (Vals)
GPT-5.6 Luna leads this result
Terminal-Bench 4.1
Not directly comparable
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
Not directly comparable
ApprenticeBench
Not directly comparable
MazeBench
Not directly comparable
Terminal-Bench 2.0
Not directly comparable
Vibe Code Bench
Not directly comparable
LiveCodeBench (Vals)
Not directly comparable
SWE-bench (Vals)
GPT-5.6 Luna leads this result
SWE-bench Pro
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
DeepSWE
Not directly comparable
FrontierCode 1.1 Extended
Not directly comparable
CursorBench 3.2
Not directly comparable
VulcanBench v3
Not directly comparable
CursorBench 4.0
Not directly comparable
ExtractBench (LlamaIndex)
Shared sourceGPT-5.6 Luna leads this result
ParseBench
Shared sourceGPT-5.6 Luna leads this result
MMMU-Pro
GPT-5.6 Luna leads this result
MMMU-Pro w/ Python
GPT-5.6 Luna leads this result
GPQA
GPT-5.6 Luna leads this result
HLE
Not directly comparable
HLE w/o tools
Not directly comparable
GPQA Diamond (Vals)
GPT-5.6 Luna leads this result
MMLU-Pro (Vals)
GPT-5.6 Luna leads this result
GPQA-D
Not directly comparable
HealthBench Professional
Not directly comparable
HealthBench Hard
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 7,000+ subscribers.
Last updated November 10, 2026
