Agentic
Directional only- GPT-5.6 Luna
- 56.6
- Supported · #36/157
- GPT-6 Sol
- 69.7
- Estimated · #7/157
- Basis
- BenchAlign lane · 9 vs 4 public rows
- Reading
- Directional only
GPT-5.6 Luna vs GPT-6 Sol
Decision reading
GPT-6 Sol has the higher public score estimate, 80.45 versus 62.23, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
5 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Updated September 22, 2026. Rank says GPT-6 Sol is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
Share or export
Which one for your work
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.
Chat turn cost
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.
Confidence: listed-rates
Cache-heavy agent loop cost
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.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
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.
Confidence: listed-rates
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
GPT-6 Sol is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
GPT-6 Sol is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
Which one for a specific job
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.
66.5GPT-5.6 Luna74.3GPT-6 Sol
Directional only · BenchAlign
GPT-6 Sol scores higher, but at least one score rests on Estimated evidence or a different benchmark set. Directional only, no winner.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
24 GPT-5.6 Luna only
5 Shared
5 GPT-6 Sol only
- Shared results
- 5
- GPT-5.6 Luna only
- 24
- GPT-6 Sol only
- 5
- Like-for-like categories
- 0 / 8
4 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign 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.
Coding
Directional only- GPT-5.6 Luna
- 66.5
- Supported · #13/159
- GPT-6 Sol
- 74.3
- Estimated · #6/159
- Basis
- BenchAlign lane · 7 vs 1 public rows
- Reading
- Directional only
Reasoning
Directional only- GPT-5.6 Luna
- 50.8
- #16/17
- GPT-6 Sol
- 78.5
- #5/17
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Directional only
Knowledge
Directional only- GPT-5.6 Luna
- 63.5
- Supported · #30/189
- GPT-6 Sol
- 80.2
- Estimated · #6/189
- Basis
- BenchAlign lane · 6 vs 5 public rows
- Reading
- Directional only
Multimodal
Not comparable- GPT-5.6 Luna
- 67.1
- #22/50
- GPT-6 Sol
- 82.8
- Unranked · 1 rankable row
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- GPT-5.6 Luna
- Not ranked
- GPT-6 Sol
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- GPT-5.6 Luna
- Not ranked
- GPT-6 Sol
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- GPT-5.6 Luna
- 94.2
- Unranked · 3 rankable rows
- GPT-6 Sol
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
| Category | GPT-5.6 Luna | GPT-6 Sol | Basis | Reading |
|---|---|---|---|---|
| Agentic | 56.6Supported · #36/157 | 69.7Estimated · #7/157 | Directional onlyBenchAlign lane · 9 vs 4 public rows | Directional only |
| Coding | 66.5Supported · #13/159 | 74.3Estimated · #6/159 | Directional onlyBenchAlign lane · 7 vs 1 public rows | Directional only |
| Reasoning | 50.8#16/17 | 78.5#5/17 | Directional onlyProvisional lane · 2 vs 0 weighted rows | Directional only |
| Knowledge | 63.5Supported · #30/189 | 80.2Estimated · #6/189 | Directional onlyBenchAlign lane · 6 vs 5 public rows | Directional only |
| Multimodal | 67.1#22/50 | 82.8Unranked · 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 | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 94.2Unranked · 3 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Shape of the matched evidence
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.
OSWorld 2.0
Agentic
What each workload costs
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.
Chat turn
1K fresh input + 500 output tokens
- GPT-5.6 Luna
- $0.0008
- Fits in one request
- GPT-6 Sol
- $0.007
- Fits in one request
GPT-5.6 Luna has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- GPT-5.6 Luna
- $0.0136
- Fits in one request
- GPT-6 Sol
- $0.13
- Fits in one request
GPT-5.6 Luna has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GPT-5.6 Luna
- $0.02
- Fits in one request
- GPT-6 Sol
- $0.18
- Fits in one request
GPT-5.6 Luna has the lower modeled cost
Costs use the listed standard API rates.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGPT-5.6 LunaGPT-6 Sol
Context window
Maximum documented context; output-token limits may be lower.
GPT-5.6 Luna
1.05M
OpenAI model catalogGPT-6 Sol
API model ID
GPT-5.6 Luna
gpt-5.6-luna
OpenAI model catalogGPT-6 Sol
gpt-6-sol
OpenAI GPT-6 Sol model documentationCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GPT-5.6 Luna
$0.02 per 1M cached input tokens
OpenAI pricingGPT-6 Sol
$0.2 per 1M cached input tokens
OpenAI GPT-6 Sol model documentationDocumented inputs
GPT-5.6 Luna
text, image
OpenAI model catalogGPT-6 Sol
text, image
OpenAI GPT-6 Sol model documentationDocumented outputs
GPT-5.6 Luna
GPT-6 Sol
Provider availability
GPT-5.6 Luna
Generally Available · OpenAI Responses API
OpenAI model catalogGPT-6 Sol
Generally Available · OpenAI Responses API, OpenAI Chat Completions API, ChatGPT Work, Codex
OpenAI GPT-6 Sol and Luna launchReasoning profile
GPT-5.6 Luna
Reasoning
GPT-6 Sol
Reasoning
Weight access
GPT-5.6 Luna
Proprietary
GPT-6 Sol
Proprietary
License
GPT-5.6 Luna
Proprietary
GPT-6 Sol
Proprietary
Release date
GPT-5.6 Luna
2026-07-09
GPT-6 Sol
2026-09-16
If you already use one of these models
- Deployment change
- Both entries list OpenAI as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- GPT-6 Sol has the higher public score estimate, 80.45 versus 62.23, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.0136 vs $0.13. Cache-heavy agent loop: $0.02 vs $0.18.
- Context tradeoff
- Both models list 1.05M.
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence34 rows
Agentic
Terminal-Bench 3.0
GPT-5.6 Luna14.3%SourceGPT-6 Sol—Not directly comparable
Terminal-Bench 2.0
GPT-5.6 Luna84.7%SourceGPT-6 Sol—Not directly comparable
BrowseComp
GPT-5.6 Luna83.3%SourceGPT-6 Sol—Not directly comparable
OSWorld 2.0
GPT-5.6 Luna45.6%SourceGPT-6 Sol60.5%SourceGPT-6 Sol leads this result
CyberGym
GPT-5.6 Luna77.9%SourceGPT-6 Sol—Not directly comparable
ExploitGym
GPT-5.6 Luna12.4%SourceGPT-6 Sol22.1%SourceGPT-6 Sol leads this result
Toolathlon
GPT-5.6 Luna53.4%SourceGPT-6 Sol—Not directly comparable
Terminal-Bench 2.1 (Vals)
GPT-5.6 Luna79.0%SourceGPT-6 Sol—Not directly comparable
ApprenticeBench
GPT-5.6 Luna7%SourceGPT-6 Sol—Not directly comparable
Agents' Last Exam
GPT-5.6 Luna—GPT-6 Sol56.4%SourceNot directly comparable
AutomationBench
GPT-5.6 Luna—GPT-6 Sol33.2%SourceNot directly comparable
Coding
SWE-bench Pro
GPT-5.6 Luna62.7%SourceGPT-6 Sol—Not directly comparable
Terminal-Bench 2.0
GPT-5.6 Luna84.7%SourceGPT-6 Sol—Not directly comparable
DeepSWE
GPT-5.6 Luna67.2%SourceGPT-6 Sol68.8%SourceGPT-6 Sol leads this result
FrontierCode 1.1 Extended
GPT-5.6 Luna55.1%SourceGPT-6 Sol—Not directly comparable
cursorBench32
GPT-5.6 Luna61.1%SourceGPT-6 Sol—Not directly comparable
VulcanBench v3
GPT-5.6 Luna85.5%SourceGPT-6 Sol—Not directly comparable
SWE-bench (Vals)
GPT-5.6 Luna93.0%SourceGPT-6 Sol—Not directly comparable
Reasoning
Multimodal
Knowledge
GPQA
GPT-5.6 Luna92.3%SourceGPT-6 Sol—Not directly comparable
GPQA-D
GPT-5.6 Luna92.3%SourceGPT-6 Sol—Not directly comparable
HealthBench Professional
GPT-5.6 Luna55.7%SourceGPT-6 Sol60.8%SourceGPT-6 Sol leads this result
HealthBench Hard
GPT-5.6 Luna32.0%SourceGPT-6 Sol30.1%SourceGPT-5.6 Luna leads this result
GPQA Diamond (Vals)
GPT-5.6 Luna91.7%SourceGPT-6 Sol—Not directly comparable
MMLU-Pro (Vals)
GPT-5.6 Luna86.0%SourceGPT-6 Sol—Not directly comparable
HealthBench (raw)
GPT-5.6 Luna—GPT-6 Sol47.1%SourceNot directly comparable
HealthBench (length-adjusted)
GPT-5.6 Luna—GPT-6 Sol53.2%SourceNot directly comparable
HealthBench Professional (raw)
GPT-5.6 Luna—GPT-6 Sol59.5%SourceNot directly comparable
Math
Questions
Which is better, GPT-5.6 Luna or GPT-6 Sol?
GPT-6 Sol has the higher public score estimate, 80.45 versus 62.23, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, GPT-5.6 Luna or GPT-6 Sol?
GPT-6 Sol scores higher for coding on the public lane, 74.3 to 66.5. GPT-6 Sol is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, GPT-5.6 Luna or GPT-6 Sol?
GPT-6 Sol scores higher for agentic tasks on the public lane, 69.7 to 56.6. GPT-6 Sol 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.
Which costs less, GPT-5.6 Luna or GPT-6 Sol?
For the stated presets, chat costs $0.0008 on GPT-5.6 Luna and $0.007 on GPT-6 Sol; repository review costs $0.0136 and $0.13; the cache-heavy agent loop costs $0.02 and $0.18. Costs use the listed standard API rates.
Which has the larger context window, GPT-5.6 Luna or GPT-6 Sol?
Both models list the same context window, 1.05M.
Related comparisons
Last updated September 22, 2026
Watch GPT-5.6 Luna vs GPT-6 Sol
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.