Agentic
Like-for-like- GPT-5.6 Luna
- 56.5
- Supported · #34/151
- Ling 3.0 Flash
- 40.0
- Supported · #121/151
- Basis
- BenchAlign lane · 8 vs 7 public rows
- Reading
- GPT-5.6 Luna leads · intervals overlap
GPT-5.6 Luna vs Ling 3.0 Flash
Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
GPT-5.6 Luna has the higher public score estimate, 65.54 versus 52.2, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
8 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
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.
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, 56.5 to 40, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Long 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
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Ling 3.0 Flash is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
20 GPT-5.6 Luna only
8 Shared
14 Ling 3.0 Flash only
- Shared results
- 8
- GPT-5.6 Luna only
- 20
- Ling 3.0 Flash only
- 14
- Like-for-like categories
- 2 / 8
1 category rests 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.
Knowledge
Like-for-like- GPT-5.6 Luna
- 64.7
- Supported · #27/181
- Ling 3.0 Flash
- 45.9
- Supported · #112/181
- Basis
- BenchAlign lane · 6 vs 5 public rows
- Reading
- GPT-5.6 Luna leads · intervals overlap
Coding
Directional only- GPT-5.6 Luna
- 66.9
- Supported · #10/183
- Ling 3.0 Flash
- 42.8
- Estimated · #126/183
- Basis
- BenchAlign lane · 7 vs 6 public rows
- Reading
- Directional only
Reasoning
Not comparable- GPT-5.6 Luna
- 50.4
- #21/22
- Ling 3.0 Flash
- 69.2
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- GPT-5.6 Luna
- 94.4
- Unranked · 3 rankable rows
- Ling 3.0 Flash
- 73.7
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 2 vs 2 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- GPT-5.6 Luna
- Not ranked
- Ling 3.0 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- GPT-5.6 Luna
- 67.0
- #21/48
- Ling 3.0 Flash
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- GPT-5.6 Luna
- Not ranked
- Ling 3.0 Flash
- 75.6
- #58/120
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
| Category | GPT-5.6 Luna | Ling 3.0 Flash | Basis | Reading |
|---|---|---|---|---|
| Agentic | 56.5Supported · #34/151 | 40.0Supported · #121/151 | Like-for-likeBenchAlign lane · 8 vs 7 public rows | GPT-5.6 Luna leads · intervals overlap |
| Knowledge | 64.7Supported · #27/181 | 45.9Supported · #112/181 | Like-for-likeBenchAlign lane · 6 vs 5 public rows | GPT-5.6 Luna leads · intervals overlap |
| Coding | 66.9Supported · #10/183 | 42.8Estimated · #126/183 | Directional onlyBenchAlign lane · 7 vs 6 public rows | Directional only |
| Reasoning | 50.4#21/22 | 69.2Unranked · 2 rankable rows | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Math | 94.4Unranked · 3 rankable rows | 73.7Unranked · 3 rankable rows | Not comparableProvisional lane · 2 vs 2 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 67.0#21/48 | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | 75.6#58/120 | Not comparableProvisional lane · 0 vs 1 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.
BrowseComp
Agentic
GPT-5.6 Luna: 83.3%Ling 3.0 Flash: 72.2%Normalized gap 11.1GPT-5.6 Luna source Ling 3.0 Flash sourceGPQA
Knowledge
SWE-bench Pro
Coding
MMLU-Pro (Vals)
Knowledge
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
- $0.004
- Fits in one request
- Ling 3.0 Flash
- API rate not published
- Fits in one request
Ling 3.0 Flash has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- GPT-5.6 Luna
- $0.068
- Fits in one request
- Ling 3.0 Flash
- API rate not published
- Fits in one request
Ling 3.0 Flash has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GPT-5.6 Luna
- $0.1
- Fits in one request
- Ling 3.0 Flash
- API rate not published
- Fits in one request
- Cached-input rate unavailable
Ling 3.0 Flash has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGPT-5.6 LunaLing 3.0 Flash
Context window
Maximum documented context; output-token limits may be lower.
GPT-5.6 Luna
1.05M
OpenAI model catalogLing 3.0 Flash
API model ID
GPT-5.6 Luna
gpt-5.6-luna
OpenAI model catalogLing 3.0 Flash
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GPT-5.6 Luna
$0.1 per 1M cached input tokens
OpenAI API pricingLing 3.0 Flash
No comparable hosted API rate
InclusionAI Ling 3.0 Flash model cardDocumented inputs
GPT-5.6 Luna
text, image
OpenAI model catalogLing 3.0 Flash
Not sourced
Documented outputs
GPT-5.6 Luna
Ling 3.0 Flash
Not sourced
Provider availability
GPT-5.6 Luna
Generally Available · OpenAI Responses API
OpenAI model catalogLing 3.0 Flash
Not sourced
Reasoning profile
GPT-5.6 Luna
Reasoning
Ling 3.0 Flash
Reasoning
Weight access
GPT-5.6 Luna
Proprietary
Ling 3.0 Flash
Open Weight
License
GPT-5.6 Luna
Proprietary
Ling 3.0 Flash
Open Weight
Release date
GPT-5.6 Luna
2026-07-09
Ling 3.0 Flash
2026-07-23
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, 65.54 versus 52.2, but the 90% score intervals overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- 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.
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 3.0
GPT-5.6 Luna14.3%SourceLing 3.0 Flash—Not directly comparable
Terminal-Bench 2.0
GPT-5.6 Luna84.7%SourceLing 3.0 Flash—Not directly comparable
BrowseComp
GPT-5.6 Luna83.3%SourceLing 3.0 Flash72.2%SourceGPT-5.6 Luna leads this result
OSWorld 2.0
GPT-5.6 Luna45.6%SourceLing 3.0 Flash—Not directly comparable
CyberGym
GPT-5.6 Luna77.9%SourceLing 3.0 Flash—Not directly comparable
ExploitGym
GPT-5.6 Luna12.4%SourceLing 3.0 Flash—Not directly comparable
Toolathlon
GPT-5.6 Luna53.4%SourceLing 3.0 Flash—Not directly comparable
Terminal-Bench 2.1 (Vals)
GPT-5.6 Luna79.0%SourceLing 3.0 Flash50.2%SourceGPT-5.6 Luna leads this result
MCP Atlas
GPT-5.6 Luna—Ling 3.0 Flash65.5%SourceNot directly comparable
skillsBench
GPT-5.6 Luna—Ling 3.0 Flash44.8%SourceNot directly comparable
BFCL v4
GPT-5.6 Luna—Ling 3.0 Flash73.0%SourceNot directly comparable
WideResearch
GPT-5.6 Luna—Ling 3.0 Flash73.6%SourceNot directly comparable
DRACO
GPT-5.6 Luna—Ling 3.0 Flash70.4%SourceNot directly comparable
Coding
SWE-bench Pro
GPT-5.6 Luna62.7%SourceLing 3.0 Flash56.6%SourceGPT-5.6 Luna leads this result
Terminal-Bench 2.0
GPT-5.6 Luna84.7%SourceLing 3.0 Flash—Not directly comparable
deepSwe
GPT-5.6 Luna67.2%SourceLing 3.0 Flash—Not directly comparable
FrontierCode 1.1 Extended
GPT-5.6 Luna55.1%SourceLing 3.0 Flash—Not directly comparable
cursorBench32
GPT-5.6 Luna61.1%SourceLing 3.0 Flash—Not directly comparable
VulcanBench v3
GPT-5.6 Luna85.5%SourceLing 3.0 Flash—Not directly comparable
SWE-bench (Vals)
GPT-5.6 Luna93.0%SourceLing 3.0 Flash65.2%SourceGPT-5.6 Luna leads this result
SWE Multilingual
GPT-5.6 Luna—Ling 3.0 Flash72.4%SourceNot directly comparable
LiveCodeBench v5
GPT-5.6 Luna—Ling 3.0 Flash82.8%SourceNot directly comparable
SciCode
GPT-5.6 Luna—Ling 3.0 Flash41.2%SourceNot directly comparable
LiveCodeBench (Vals)
GPT-5.6 Luna—Ling 3.0 Flash84.0%SourceNot directly comparable
Reasoning
Knowledge
GPQA
GPT-5.6 Luna92.3%SourceLing 3.0 Flash85.0%SourceGPT-5.6 Luna leads this result
GPQA-D
GPT-5.6 Luna92.3%SourceLing 3.0 Flash85.0%SourceGPT-5.6 Luna leads this result
HealthBench Professional
GPT-5.6 Luna55.7%SourceLing 3.0 Flash—Not directly comparable
HealthBench Hard
GPT-5.6 Luna32.0%SourceLing 3.0 Flash—Not directly comparable
GPQA Diamond (Vals)
GPT-5.6 Luna91.7%SourceLing 3.0 Flash84.8%SourceGPT-5.6 Luna leads this result
MMLU-Pro (Vals)
GPT-5.6 Luna86.0%SourceLing 3.0 Flash82.0%SourceGPT-5.6 Luna leads this result
HLE
GPT-5.6 Luna—Ling 3.0 Flash22.7%SourceNot directly comparable
Math
FrontierMath (legacy)
GPT-5.6 Luna78.6%SourceLing 3.0 Flash—Not directly comparable
FrontierMath v2 (Tiers 1-3)
GPT-5.6 Luna78.600%SourceLing 3.0 Flash—Not directly comparable
FrontierMath v2 (Tier 4)
GPT-5.6 Luna58.500%SourceLing 3.0 Flash—Not directly comparable
AIME26
GPT-5.6 Luna—Ling 3.0 Flash93.2%SourceNot directly comparable
HMMT Feb 2026
GPT-5.6 Luna—Ling 3.0 Flash87.0%SourceNot directly comparable
IMOAnswerBench
GPT-5.6 Luna—Ling 3.0 Flash83.7%SourceNot directly comparable
Multimodal
Instruction following
IFBench
GPT-5.6 Luna—Ling 3.0 Flash74.5%SourceNot directly comparable
Frequently asked questions
Which is better, GPT-5.6 Luna or Ling 3.0 Flash?
GPT-5.6 Luna has the higher public score estimate, 65.54 versus 52.2, 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 Ling 3.0 Flash?
GPT-5.6 Luna scores higher for coding on the public lane, 66.9 to 42.8. Ling 3.0 Flash 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 Ling 3.0 Flash?
GPT-5.6 Luna leads the public agentic tasks lane, 56.5 to 40, with Supported evidence for both models, although the 90% intervals overlap.
Which costs less, GPT-5.6 Luna or Ling 3.0 Flash?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, GPT-5.6 Luna or Ling 3.0 Flash?
GPT-5.6 Luna has the larger documented context window: 1.05M, compared with 262K.
Related comparisons
Last updated September 4, 2026
Watch GPT-5.6 Luna vs Ling 3.0 Flash
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.