Long documents
Prompts that approach the documented context limit
GPT-6 Luna
GPT-6 Luna has the larger documented context window.
Confidence: documented
Claude Sonnet 5.5 vs GPT-6 Luna
Updated September 28, 2026. Rank says Claude Sonnet 5.5 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
Decision reading
Claude Sonnet 5.5 has the higher public score estimate, 80.49 versus 66.45, 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.
- Shared results
- 5
- Claude Sonnet 5.5 only
- 42
- GPT-6 Luna only
- 5
- Like-for-like categories
- 1 / 8
Estimated: Claude Sonnet 5.5 and GPT-6 LunaHow the comparison works
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-6 Luna
GPT-6 Luna has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesCache-heavy agent loop cost
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.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
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.
Confidence: listed-ratesCoding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Claude Sonnet 5.5 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limitedAgentic work
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.
Confidence: limited
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.
79.6Claude Sonnet 5.551.1GPT-6 Luna
Directional only · BenchAlign v5.7
Claude Sonnet 5.5 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.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
42 Claude Sonnet 5.5 only
5 Shared
5 GPT-6 Luna only
3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign v5.7 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.
Knowledge
Like-for-like- Claude Sonnet 5.5
- 80.9
- Supported · #6/160
- GPT-6 Luna
- 65.3
- Supported · #21/160
- Basis
- BenchAlign v5.7 lane · 16 vs 5 public rows
- Reading
- Claude Sonnet 5.5 leads · intervals overlap
Agentic
Directional only- Claude Sonnet 5.5
- 66.1
- Supported · #10/111
- GPT-6 Luna
- 55.5
- Estimated · #29/111
- Basis
- BenchAlign v5.7 lane · 11 vs 1 public rows
- Reading
- Directional only
Coding
Directional only- Claude Sonnet 5.5
- 79.6
- Estimated · #3/136
- GPT-6 Luna
- 51.1
- Supported · #35/136
- Basis
- BenchAlign v5.7 lane · 9 vs 1 public rows
- Reading
- Directional only
Reasoning
Directional only- Claude Sonnet 5.5
- 79.2
- #7/27
- GPT-6 Luna
- 55.6
- #25/27
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Directional only
Multimodal
Not comparable- Claude Sonnet 5.5
- 83.3
- Unranked · 7 rankable rows
- GPT-6 Luna
- 72.3
- Unranked · 1 rankable row
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Sonnet 5.5
- Not ranked
- GPT-6 Luna
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Sonnet 5.5
- Not ranked
- GPT-6 Luna
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Sonnet 5.5
- Not ranked
- GPT-6 Luna
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Sonnet 5.5 | GPT-6 Luna | Basis | Reading |
|---|---|---|---|---|
| Knowledge | 80.9Supported · #6/160 | 65.3Supported · #21/160 | Like-for-likeBenchAlign v5.7 lane · 16 vs 5 public rows | Claude Sonnet 5.5 leads · intervals overlap |
| Agentic | 66.1Supported · #10/111 | 55.5Estimated · #29/111 | Directional onlyBenchAlign v5.7 lane · 11 vs 1 public rows | Directional only |
| Coding | 79.6Estimated · #3/136 | 51.1Supported · #35/136 | Directional onlyBenchAlign v5.7 lane · 9 vs 1 public rows | Directional only |
| Reasoning | 79.2#7/27 | 55.6#25/27 | Directional onlyProvisional lane · 0 vs 2 weighted rows | Directional only |
| Multimodal | 83.3Unranked · 7 rankable rows | 72.3Unranked · 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 | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.7) 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.
Supported evidence per lane · bars run 0–100Methodology
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
- Claude Sonnet 5.5
- $0.007
- Fits in one request
- GPT-6 Luna
- $0.00035
- Fits in one request
GPT-6 Luna has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Sonnet 5.5
- $0.13
- Fits in one request
- GPT-6 Luna
- $0.0065
- Fits in one request
GPT-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
- Claude Sonnet 5.5
- $0.18
- Fits in one request
- GPT-6 Luna
- $0.009
- Fits in one request
GPT-6 Luna has the lower modeled cost
Costs use the listed standard API rates.
Cached input falls back to the list input rate only where a cached rate is unpublished
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Sonnet 5.5GPT-6 Luna
Context window
Maximum documented context; output-token limits may be lower.
Claude Sonnet 5.5
GPT-6 Luna
API model ID
Claude Sonnet 5.5
claude-sonnet-5-5
Anthropic Claude Sonnet 5.5 model documentationGPT-6 Luna
gpt-6-luna
OpenAI GPT-6 Luna model documentationCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Sonnet 5.5
$0.2 per 1M cached input tokens
Claude API pricingGPT-6 Luna
$0.01 per 1M cached input tokens
OpenAI GPT-6 Luna model documentationDocumented inputs
Claude Sonnet 5.5
GPT-6 Luna
text, image
OpenAI GPT-6 Luna model documentationDocumented outputs
Claude Sonnet 5.5
GPT-6 Luna
Provider availability
Claude Sonnet 5.5
Generally Available · Claude API, Amazon Bedrock, Google Cloud, Microsoft Foundry, Claude Platform on AWS
Anthropic Claude Sonnet 5.5 model documentationGPT-6 Luna
Generally Available · OpenAI Responses API, OpenAI Chat Completions API, ChatGPT Work, Codex
OpenAI GPT-6 Sol and Luna launchReasoning profile
Claude Sonnet 5.5
Reasoning
GPT-6 Luna
Reasoning
Weight access
Claude Sonnet 5.5
Proprietary
GPT-6 Luna
Proprietary
License
Claude Sonnet 5.5
Proprietary
GPT-6 Luna
Proprietary
Release date
Claude Sonnet 5.5
2026-09-28
GPT-6 Luna
2026-09-22
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- Claude Sonnet 5.5 has the higher public score estimate, 80.49 versus 66.45, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.13 vs $0.0065. Cache-heavy agent loop: $0.18 vs $0.009.
- Context tradeoff
- GPT-6 Luna has the larger documented window (1.05M).
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Claude Sonnet 5.5 or GPT-6 Luna?
Claude Sonnet 5.5 has the higher public score estimate, 80.49 versus 66.45, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Claude Sonnet 5.5 or GPT-6 Luna?
Claude Sonnet 5.5 scores higher for coding on the public lane, 79.6 to 51.1. Claude Sonnet 5.5 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, Claude Sonnet 5.5 or GPT-6 Luna?
Claude Sonnet 5.5 scores higher for agentic tasks on the public lane, 66.1 to 55.5. 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.
Which costs less, Claude Sonnet 5.5 or GPT-6 Luna?
For the stated presets, chat costs $0.007 on Claude Sonnet 5.5 and $0.00035 on GPT-6 Luna; repository review costs $0.13 and $0.0065; the cache-heavy agent loop costs $0.18 and $0.009. Costs use the listed standard API rates.
Which has the larger context window, Claude Sonnet 5.5 or GPT-6 Luna?
GPT-6 Luna has the larger documented context window: 1.05M, compared with 1M.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence52 rows
Agentic
Terminal-Bench 4.0
Claude Sonnet 5.570.60%SourceGPT-6 Luna—Not directly comparable
HLE w/ tools
Claude Sonnet 5.564.5%SourceGPT-6 Luna—Not directly comparable
DRACO
Claude Sonnet 5.587.0%SourceGPT-6 Luna—Not directly comparable
Terminal-Bench-Science 0.1
Claude Sonnet 5.559.9%SourceGPT-6 Luna—Not directly comparable
LAB all-pass (Harvey held-out)
Claude Sonnet 5.510.0%SourceGPT-6 Luna—Not directly comparable
LAB criterion-pass (Harvey held-out)
Claude Sonnet 5.593.1%SourceGPT-6 Luna—Not directly comparable
Toolathlon Verified Pass@3
Claude Sonnet 5.585.2%SourceGPT-6 Luna—Not directly comparable
Toolathlon Verified Pass³
Claude Sonnet 5.568.5%SourceGPT-6 Luna—Not directly comparable
Toolathlon Verified avg. turns
Claude Sonnet 5.531.6 turnsSourceGPT-6 Luna—Not directly comparable
AutomationBench (Zapier 1.0.6)
Claude Sonnet 5.544.7%SourceGPT-6 Luna—Not directly comparable
Toolathlon-Verified
Claude Sonnet 5.577.8%SourceGPT-6 Luna—Not directly comparable
ExploitGym
Claude Sonnet 5.5—GPT-6 Luna11.6%SourceNot directly comparable
Coding
FrontierCode 1.1 Main
Claude Sonnet 5.546.2%SourceGPT-6 Luna—Not directly comparable
cursorBench40
Claude Sonnet 5.555.5%SourceGPT-6 Luna—Not directly comparable
SWE-bench Pro
Claude Sonnet 5.581.3%SourceGPT-6 Luna—Not directly comparable
SWE Multilingual
Claude Sonnet 5.590.3%SourceGPT-6 Luna—Not directly comparable
SWE Multimodal
Claude Sonnet 5.554.3%SourceGPT-6 Luna—Not directly comparable
DeepSWE
Claude Sonnet 5.571.0%SourceGPT-6 Luna66.6%SourceClaude Sonnet 5.5 leads this result
FrontierCode 1.1 Extended
Claude Sonnet 5.559.1%SourceGPT-6 Luna—Not directly comparable
ProgramBench
Claude Sonnet 5.579.7%SourceGPT-6 Luna—Not directly comparable
FrontierSWE v2
Claude Sonnet 5.561.9%SourceGPT-6 Luna—Not directly comparable
Reasoning
Multimodal
Chartography (no tools)
Claude Sonnet 5.561.6%SourceGPT-6 Luna—Not directly comparable
Chartography (tools)
Claude Sonnet 5.590.2%SourceGPT-6 Luna—Not directly comparable
BenchCAD Vision2Code (no tools)
Claude Sonnet 5.50.747SourceGPT-6 Luna—Not directly comparable
BenchCAD Vision2Code (tools)
Claude Sonnet 5.50.963SourceGPT-6 Luna—Not directly comparable
Biomedical image analysis
Claude Sonnet 5.572.2%SourceGPT-6 Luna—Not directly comparable
OfficeQA
Claude Sonnet 5.576.9%SourceGPT-6 Luna—Not directly comparable
OfficeQA Pro
Claude Sonnet 5.565.6%SourceGPT-6 Luna—Not directly comparable
Knowledge
HealthBench (raw)
Claude Sonnet 5.569.4%SourceGPT-6 Luna50.0%SourceClaude Sonnet 5.5 leads this result
HealthBench (length-adjusted)
Claude Sonnet 5.565.4%SourceGPT-6 Luna54.5%SourceClaude Sonnet 5.5 leads this result
HealthBench Professional (raw)
Claude Sonnet 5.577.1%SourceGPT-6 Luna61.2%SourceClaude Sonnet 5.5 leads this result
HealthBench Professional
Claude Sonnet 5.569.2%SourceGPT-6 Luna60.8%SourceClaude Sonnet 5.5 leads this result
BioMysteryBench (human-solvable)
Claude Sonnet 5.589.2%SourceGPT-6 Luna—Not directly comparable
BioMysteryBench (human-difficult)
Claude Sonnet 5.544.7%SourceGPT-6 Luna—Not directly comparable
SpatialBench Verified
Claude Sonnet 5.572.5%SourceGPT-6 Luna—Not directly comparable
SingleCellBench
Claude Sonnet 5.559.1%SourceGPT-6 Luna—Not directly comparable
Protein Design
Claude Sonnet 5.551.0%SourceGPT-6 Luna—Not directly comparable
Morphology-to-molecule matching
Claude Sonnet 5.525.0%SourceGPT-6 Luna—Not directly comparable
Medicinal chemistry
Claude Sonnet 5.565.3%SourceGPT-6 Luna—Not directly comparable
Protein Design library ranking
Claude Sonnet 5.554.8%SourceGPT-6 Luna—Not directly comparable
De novo protein-binder design
Claude Sonnet 5.582.3%SourceGPT-6 Luna—Not directly comparable
Protocols (troubleshooting)
Claude Sonnet 5.567.3%SourceGPT-6 Luna—Not directly comparable
Protocols (understanding)
Claude Sonnet 5.566.6%SourceGPT-6 Luna—Not directly comparable
HLE w/o tools
Claude Sonnet 5.556.9%SourceGPT-6 Luna—Not directly comparable
HealthBench Hard
Claude Sonnet 5.5—GPT-6 Luna31.4%SourceNot directly comparable
Multilingual
Math
52 public results · 5 shared
Watch Claude Sonnet 5.5 vs GPT-6 Luna
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.
Last updated September 28, 2026