Coding work
Code generation, repair, and software-engineering tasks
GPT-5.6 Luna
GPT-5.6 Luna leads on the public coding lane, 64.5 to 53.2, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Gemini 3.5 Flash vs GPT-5.6 Luna
Updated September 24, 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.
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
GPT-5.6 Luna has the higher public score estimate, 65.6 versus 63.49, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 14 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 14
- Gemini 3.5 Flash only
- 13
- GPT-5.6 Luna only
- 15
- Like-for-like categories
- 3 / 8
Supported: Gemini 3.5 Flash and GPT-5.6 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.
Agentic work
Tool use, computer use, and multi-step task completion
GPT-5.6 Luna
GPT-5.6 Luna leads on the public agentic lane, 55.3 to 50, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limitedLong documents
Prompts that approach the documented context limit
GPT-5.6 Luna
GPT-5.6 Luna has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
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-ratesCache-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-ratesRepository 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
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.
53.2Gemini 3.5 Flash64.5GPT-5.6 Luna
Like-for-like · BenchAlign v5.7
GPT-5.6 Luna leads the like-for-like coding row, although the 90% intervals overlap.
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.
13 Gemini 3.5 Flash only
14 Shared
15 GPT-5.6 Luna only
2 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.
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.
FrontierMath v2 (Tier 4)Math
Normalized gap 43.9Gemini 3.5 Flash:14.583%GPT-5.6 Luna:58.500%FrontierMath v2 (Tiers 1-3)Math
Normalized gap 39.6Gemini 3.5 Flash:38.966%GPT-5.6 Luna:78.600%ARC-AGI-2Reasoning
Normalized gap 12.6Gemini 3.5 Flash:72.1%GPT-5.6 Luna:59.5%cursorBench32Coding
Normalized gap 12.3Gemini 3.5 Flash:48.8%GPT-5.6 Luna:61.1%SWE-bench ProCoding
Normalized gap 7.6Gemini 3.5 Flash:55.1%GPT-5.6 Luna:62.7%
Bars run 0–100 on each benchmark’s normalized display scale
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.
Agentic
Like-for-like- Gemini 3.5 Flash
- 50.0
- Supported · #35/105
- GPT-5.6 Luna
- 55.3
- Supported · #28/105
- Basis
- BenchAlign v5.7 lane · 8 vs 9 public rows
- Reading
- GPT-5.6 Luna leads · intervals overlap
Coding
Like-for-like- Gemini 3.5 Flash
- 53.2
- Supported · #33/135
- GPT-5.6 Luna
- 64.5
- Supported · #9/135
- Basis
- BenchAlign v5.7 lane · 7 vs 7 public rows
- Reading
- GPT-5.6 Luna leads · intervals overlap
Knowledge
Like-for-like- Gemini 3.5 Flash
- 64.4
- Supported · #24/158
- GPT-5.6 Luna
- 64.6
- Supported · #22/158
- Basis
- BenchAlign v5.7 lane · 4 vs 6 public rows
- Reading
- Practical tie
Reasoning
Directional only- Gemini 3.5 Flash
- 62.7
- #13/19
- GPT-5.6 Luna
- 54.7
- #18/19
- Basis
- Provisional lane · 2 vs 2 weighted rows
- Reading
- Directional only
Multimodal
Directional only- Gemini 3.5 Flash
- 86.8
- #7/50
- GPT-5.6 Luna
- 67.1
- #22/50
- Basis
- Provisional lane · 2 vs 1 weighted rows
- Reading
- Directional only
Multilingual
Not comparable- Gemini 3.5 Flash
- Not ranked
- GPT-5.6 Luna
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Gemini 3.5 Flash
- 84.1
- #43/124
- GPT-5.6 Luna
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Gemini 3.5 Flash
- 55.1
- Unranked · 2 rankable rows
- GPT-5.6 Luna
- 94.2
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 2 vs 2 weighted rows
- Reading
- Not comparable
| Category | Gemini 3.5 Flash | GPT-5.6 Luna | Basis | Reading |
|---|---|---|---|---|
| Agentic | 50.0Supported · #35/105 | 55.3Supported · #28/105 | Like-for-likeBenchAlign v5.7 lane · 8 vs 9 public rows | GPT-5.6 Luna leads · intervals overlap |
| Coding | 53.2Supported · #33/135 | 64.5Supported · #9/135 | Like-for-likeBenchAlign v5.7 lane · 7 vs 7 public rows | GPT-5.6 Luna leads · intervals overlap |
| Knowledge | 64.4Supported · #24/158 | 64.6Supported · #22/158 | Like-for-likeBenchAlign v5.7 lane · 4 vs 6 public rows | Practical tie |
| Reasoning | 62.7#13/19 | 54.7#18/19 | Directional onlyProvisional lane · 2 vs 2 weighted rows | Directional only |
| Multimodal | 86.8#7/50 | 67.1#22/50 | Directional onlyProvisional lane · 2 vs 1 weighted rows | Directional only |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | 84.1#43/124 | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 55.1Unranked · 2 rankable rows | 94.2Unranked · 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, 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
- Gemini 3.5 Flash
- $0.006
- Fits in one request
- GPT-5.6 Luna
- $0.0008
- 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
- Gemini 3.5 Flash
- $0.102
- Fits in one request
- GPT-5.6 Luna
- $0.0136
- 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
- Gemini 3.5 Flash
- $0.15
- Fits in one request
- GPT-5.6 Luna
- $0.02
- Fits in one request
GPT-5.6 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.
SpecificationGemini 3.5 FlashGPT-5.6 Luna
Context window
Maximum documented context; output-token limits may be lower.
Gemini 3.5 Flash
GPT-5.6 Luna
1.05M
OpenAI model catalogAPI model ID
Gemini 3.5 Flash
gemini-3.5-flash
Google Gemini API pricingGPT-5.6 Luna
gpt-5.6-luna
OpenAI model catalogCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Gemini 3.5 Flash
$0.15 per 1M cached input tokens
Google Gemini API pricingGPT-5.6 Luna
$0.02 per 1M cached input tokens
OpenAI pricingDocumented inputs
Gemini 3.5 Flash
Not sourced
GPT-5.6 Luna
text, image
OpenAI model catalogDocumented outputs
Gemini 3.5 Flash
Not sourced
GPT-5.6 Luna
Provider availability
Gemini 3.5 Flash
Not sourced
GPT-5.6 Luna
Generally Available · OpenAI Responses API
OpenAI model catalogReasoning profile
Gemini 3.5 Flash
Reasoning
GPT-5.6 Luna
Reasoning
Weight access
Gemini 3.5 Flash
Proprietary
GPT-5.6 Luna
Proprietary
License
Gemini 3.5 Flash
Proprietary
GPT-5.6 Luna
Proprietary
Release date
Gemini 3.5 Flash
2026-05-19
GPT-5.6 Luna
2026-07-09
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
- GPT-5.6 Luna has the higher public score estimate, 65.6 versus 63.49, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.102 vs $0.0136. Cache-heavy agent loop: $0.15 vs $0.02.
- Context tradeoff
- GPT-5.6 Luna has the larger documented window (1.05M).
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Gemini 3.5 Flash or GPT-5.6 Luna?
GPT-5.6 Luna has the higher public score estimate, 65.6 versus 63.49, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Gemini 3.5 Flash or GPT-5.6 Luna?
GPT-5.6 Luna leads the public coding lane, 64.5 to 53.2, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, Gemini 3.5 Flash or GPT-5.6 Luna?
GPT-5.6 Luna leads the public agentic tasks lane, 55.3 to 50, with Supported evidence for both models, although the 90% intervals overlap.
Which costs less, Gemini 3.5 Flash or GPT-5.6 Luna?
For the stated presets, chat costs $0.006 on Gemini 3.5 Flash and $0.0008 on GPT-5.6 Luna; repository review costs $0.102 and $0.0136; the cache-heavy agent loop costs $0.15 and $0.02. Costs use the listed standard API rates.
Which has the larger context window, Gemini 3.5 Flash or GPT-5.6 Luna?
GPT-5.6 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 evidence42 rows
Agentic
Terminal-Bench 2.1
Gemini 3.5 Flash76.2%SourceGPT-5.6 Luna84.7%SourceGPT-5.6 Luna leads this result
MCP Atlas
Gemini 3.5 Flash83.6%SourceGPT-5.6 Luna—Not directly comparable
Toolathlon
Gemini 3.5 Flash56.5%SourceGPT-5.6 Luna53.4%SourceGemini 3.5 Flash leads this result
OSWorld-Verified
Gemini 3.5 Flash78.4%SourceGPT-5.6 Luna—Not directly comparable
Finance Agent v2
Gemini 3.5 Flash57.9%SourceGPT-5.6 Luna—Not directly comparable
Gert Labs
Gemini 3.5 Flash61.85%SourceGPT-5.6 Luna—Not directly comparable
ResearchClawBench
Gemini 3.5 Flash18.0%SourceGPT-5.6 Luna—Not directly comparable
Terminal-Bench 2.1 (Vals)
Gemini 3.5 Flash74.2%SourceGPT-5.6 Luna79.0%SourceGPT-5.6 Luna leads this result
Terminal-Bench 3.0
Gemini 3.5 Flash—GPT-5.6 Luna14.3%SourceNot directly comparable
BrowseComp
Gemini 3.5 Flash—GPT-5.6 Luna83.3%SourceNot directly comparable
OSWorld 2.0
Gemini 3.5 Flash—GPT-5.6 Luna45.6%SourceNot directly comparable
CyberGym
Gemini 3.5 Flash—GPT-5.6 Luna77.9%SourceNot directly comparable
ExploitGym
Gemini 3.5 Flash—GPT-5.6 Luna12.4%SourceNot directly comparable
ApprenticeBench
Gemini 3.5 Flash—GPT-5.6 Luna7%SourceNot directly comparable
Coding
Terminal-Bench 2.1
Gemini 3.5 Flash76.2%SourceGPT-5.6 Luna84.7%SourceGPT-5.6 Luna leads this result
SWE-bench Pro
Gemini 3.5 Flash55.1%SourceGPT-5.6 Luna62.7%SourceGPT-5.6 Luna leads this result
Vibe Code Bench
Gemini 3.5 Flash48.68%SourceGPT-5.6 Luna—Not directly comparable
cursorBench31
Gemini 3.5 Flash49.8%SourceGPT-5.6 Luna—Not directly comparable
cursorBench32
Shared sourceGemini 3.5 Flash48.8%GPT-5.6 Luna61.1%GPT-5.6 Luna leads this result
LiveCodeBench (Vals)
Gemini 3.5 Flash87.6%SourceGPT-5.6 Luna—Not directly comparable
SWE-bench (Vals)
Gemini 3.5 Flash78.8%SourceGPT-5.6 Luna93.0%SourceGPT-5.6 Luna leads this result
DeepSWE
Gemini 3.5 Flash—GPT-5.6 Luna67.2%SourceNot directly comparable
FrontierCode 1.1 Extended
Gemini 3.5 Flash—GPT-5.6 Luna55.1%SourceNot directly comparable
VulcanBench v3
Gemini 3.5 Flash—GPT-5.6 Luna85.5%SourceNot directly comparable
Reasoning
MRCRv2
Gemini 3.5 Flash77.3%SourceGPT-5.6 Luna—Not directly comparable
MRCR 1M
Gemini 3.5 Flash26.6%SourceGPT-5.6 Luna—Not directly comparable
ARC-AGI-2
Gemini 3.5 Flash72.1%SourceGPT-5.6 Luna59.5%SourceGemini 3.5 Flash leads this result
ARC-AGI-3
Gemini 3.5 Flash—GPT-5.6 Luna0.2%SourceNot directly comparable
Multimodal
CharXiv
Gemini 3.5 Flash84.2%SourceGPT-5.6 Luna—Not directly comparable
MMMU-Pro
Gemini 3.5 Flash83.6%SourceGPT-5.6 Luna78.4%SourceGemini 3.5 Flash leads this result
Blueprint-Bench 2
Gemini 3.5 Flash33.6%SourceGPT-5.6 Luna—Not directly comparable
MMMU-Pro w/ Python
Gemini 3.5 Flash—GPT-5.6 Luna79.5%SourceNot directly comparable
Knowledge
GPQA-D
Gemini 3.5 Flash92.7%SourceGPT-5.6 Luna92.3%SourceGemini 3.5 Flash leads this result
HLE
Gemini 3.5 Flash40.2%SourceGPT-5.6 Luna—Not directly comparable
GPQA Diamond (Vals)
Gemini 3.5 Flash92.7%SourceGPT-5.6 Luna91.7%SourceGemini 3.5 Flash leads this result
MMLU-Pro (Vals)
Gemini 3.5 Flash89.5%SourceGPT-5.6 Luna86.0%SourceGemini 3.5 Flash leads this result
GPQA
Gemini 3.5 Flash—GPT-5.6 Luna92.3%SourceNot directly comparable
HealthBench Professional
Gemini 3.5 Flash—GPT-5.6 Luna55.7%SourceNot directly comparable
HealthBench Hard
Gemini 3.5 Flash—GPT-5.6 Luna32.0%SourceNot directly comparable
Math
FrontierMath v2 (Tiers 1-3)
Gemini 3.5 Flash38.966%SourceGPT-5.6 Luna78.600%SourceGPT-5.6 Luna leads this result
FrontierMath v2 (Tier 4)
Gemini 3.5 Flash14.583%SourceGPT-5.6 Luna58.500%SourceGPT-5.6 Luna leads this result
FrontierMath (legacy)
Gemini 3.5 Flash—GPT-5.6 Luna78.6%SourceNot directly comparable
42 public results · 14 shared
Watch Gemini 3.5 Flash vs GPT-5.6 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 24, 2026