Agentic
Like-for-like- GPT-5.6 Luna
- 84.1
- GPT-5.6 Sol
- 92.0
- Weighted basis
- 2 vs 2 rows
- Reading
- GPT-5.6 Sol leads
Model comparison
GPT-5.6 Luna vs GPT-5.6 Sol
Updated August 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload. This is a same-family comparison, so migration details appear when the source data supports them.
GPT-5.6 Sol has the higher public score, 81.48 versus 66.87, and the 90% score intervals do not overlap.
22 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
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.
Coding work
Code generation, repair, and software-engineering tasks
GPT-5.6 Sol
GPT-5.6 Sol leads on the same 1 weighted benchmark row.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
GPT-5.6 Sol
GPT-5.6 Sol leads on the same 2 weighted benchmark rows.
Confidence: limited
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
Show secondary and unsupported calls
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
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
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
22 Shared
2 GPT-5.6 Sol only
- Shared results
- 22
- GPT-5.6 Luna only
- 0
- GPT-5.6 Sol only
- 2
- Like-for-like categories
- 6 / 8
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Coding
Like-for-like- GPT-5.6 Luna
- 62.7
- GPT-5.6 Sol
- 64.6
- Weighted basis
- 1 vs 1 rows
- Reading
- GPT-5.6 Sol leads
Reasoning
Like-for-like- GPT-5.6 Luna
- 59.5
- GPT-5.6 Sol
- 92.5
- Weighted basis
- 1 vs 1 rows
- Reading
- GPT-5.6 Sol leads
Knowledge
Like-for-like- GPT-5.6 Luna
- 92.3
- GPT-5.6 Sol
- 94.6
- Weighted basis
- 1 vs 1 rows
- Reading
- GPT-5.6 Sol leads
Math
Like-for-like- GPT-5.6 Luna
- 73.6
- GPT-5.6 Sol
- 87.5
- Weighted basis
- 2 vs 2 rows
- Reading
- GPT-5.6 Sol leads
Multimodal
Like-for-like- GPT-5.6 Luna
- 78.4
- GPT-5.6 Sol
- 83.0
- Weighted basis
- 1 vs 1 rows
- Reading
- GPT-5.6 Sol leads
Multilingual
Not comparable- GPT-5.6 Luna
- Not measured
- GPT-5.6 Sol
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- GPT-5.6 Luna
- Not measured
- GPT-5.6 Sol
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | GPT-5.6 Luna | GPT-5.6 Sol | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 84.1 | 92.0 | Like-for-like2 vs 2 rows | GPT-5.6 Sol leads |
| Coding | 62.7 | 64.6 | Like-for-like1 vs 1 rows | GPT-5.6 Sol leads |
| Reasoning | 59.5 | 92.5 | Like-for-like1 vs 1 rows | GPT-5.6 Sol leads |
| Knowledge | 92.3 | 94.6 | Like-for-like1 vs 1 rows | GPT-5.6 Sol leads |
| Math | 73.6 | 87.5 | Like-for-like2 vs 2 rows | GPT-5.6 Sol leads |
| Multimodal | 78.4 | 83.0 | Like-for-like1 vs 1 rows | GPT-5.6 Sol leads |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
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.
ARC-AGI-2
Reasoning
FrontierMath v2 (Tier 4)
Math
FrontierMath v2 (Tiers 1-3)
Math
BrowseComp
Agentic
Terminal-Bench 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-5.6 Sol
- $0.02
- 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-5.6 Sol
- $0.34
- 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-5.6 Sol
- $0.5
- 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-5.6 Sol
Context window
Maximum documented context; output-token limits may be lower.
GPT-5.6 Luna
1.05M
OpenAI model catalogGPT-5.6 Sol
1.05M
OpenAI model catalogAPI model ID
GPT-5.6 Luna
gpt-5.6-luna
OpenAI model catalogGPT-5.6 Sol
gpt-5.6-sol
OpenAI model catalogCached-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-5.6 Sol
$0.5 per 1M cached input tokens
OpenAI pricingDocumented inputs
GPT-5.6 Luna
text, image
OpenAI model catalogGPT-5.6 Sol
text, image
OpenAI model catalogDocumented outputs
GPT-5.6 Luna
GPT-5.6 Sol
Provider availability
GPT-5.6 Luna
Generally Available · OpenAI Responses API
OpenAI model catalogGPT-5.6 Sol
Generally Available · OpenAI Responses API
OpenAI model catalogReasoning profile
GPT-5.6 Luna
Reasoning
GPT-5.6 Sol
Reasoning
Weight access
GPT-5.6 Luna
Proprietary
GPT-5.6 Sol
Proprietary
License
GPT-5.6 Luna
Proprietary
GPT-5.6 Sol
Proprietary
Release date
GPT-5.6 Luna
2026-07-09
GPT-5.6 Sol
2026-07-09
If you are choosing between sibling variants
- Deployment change
- Both entries list OpenAI as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- GPT-5.6 Sol has the higher public score, 81.48 versus 66.87, and the 90% score intervals do not overlap.
- Workload cost
- Repository review: $0.0136 vs $0.34. Cache-heavy agent loop: $0.02 vs $0.5.
- 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 evidence24 rows
Agentic
Terminal-Bench 2.0
Shared sourceGPT-5.6 Luna84.7%GPT-5.6 Sol91.9%GPT-5.6 Sol leads this result
BrowseComp
Shared sourceGPT-5.6 Luna83.3%GPT-5.6 Sol92.2%GPT-5.6 Sol leads this result
OSWorld 2.0
Shared sourceGPT-5.6 Luna45.6%GPT-5.6 Sol62.6%GPT-5.6 Sol leads this result
CyberGym
Shared sourceGPT-5.6 Luna77.9%GPT-5.6 Sol84.5%GPT-5.6 Sol leads this result
ExploitGym
Shared sourceGPT-5.6 Luna12.4%GPT-5.6 Sol33.7%GPT-5.6 Sol leads this result
Toolathlon
Shared sourceGPT-5.6 Luna53.4%GPT-5.6 Sol58%GPT-5.6 Sol leads this result
Coding
SWE-bench Pro
Shared sourceGPT-5.6 Luna62.7%GPT-5.6 Sol64.6%GPT-5.6 Sol leads this result
Terminal-Bench 2.0
Shared sourceGPT-5.6 Luna84.7%GPT-5.6 Sol91.9%GPT-5.6 Sol leads this result
deepSwe
Shared sourceGPT-5.6 Luna67.2%GPT-5.6 Sol72.7%GPT-5.6 Sol leads this result
FrontierCode 1.1 Extended
Shared sourceGPT-5.6 Luna55.1%GPT-5.6 Sol60.6%GPT-5.6 Sol leads this result
cursorBench32
Shared sourceGPT-5.6 Luna61.1%GPT-5.6 Sol67.2%GPT-5.6 Sol leads this result
VulcanBench v3
GPT-5.6 Luna—GPT-5.6 Sol87.0%SourceNot directly comparable
Reasoning
ARC-AGI-2
Shared sourceGPT-5.6 Luna59.5%GPT-5.6 Sol92.5%GPT-5.6 Sol leads this result
ARC-AGI-3
Shared sourceGPT-5.6 Luna0.2%GPT-5.6 Sol7.8%GPT-5.6 Sol leads this result
GeneBench-Pro
GPT-5.6 Luna—GPT-5.6 Sol28.7%SourceNot directly comparable
Knowledge
GPQA
Shared sourceGPT-5.6 Luna92.3%GPT-5.6 Sol94.6%GPT-5.6 Sol leads this result
GPQA-D
Shared sourceGPT-5.6 Luna92.3%GPT-5.6 Sol94.6%GPT-5.6 Sol leads this result
HealthBench Professional
Shared sourceGPT-5.6 Luna55.7%GPT-5.6 Sol60.5%GPT-5.6 Sol leads this result
HealthBench Hard
Shared sourceGPT-5.6 Luna32.0%GPT-5.6 Sol33.1%GPT-5.6 Sol leads this result
Math
FrontierMath (legacy)
Shared sourceGPT-5.6 Luna78.6%GPT-5.6 Sol89%GPT-5.6 Sol leads this result
FrontierMath v2 (Tiers 1-3)
Shared sourceGPT-5.6 Luna78.600%GPT-5.6 Sol89.000%GPT-5.6 Sol leads this result
FrontierMath v2 (Tier 4)
Shared sourceGPT-5.6 Luna58.500%GPT-5.6 Sol83.000%GPT-5.6 Sol leads this result
Multimodal
MMMU-Pro
Shared sourceGPT-5.6 Luna78.4%GPT-5.6 Sol83%GPT-5.6 Sol leads this result
MMMU-Pro w/ Python
Shared sourceGPT-5.6 Luna79.5%GPT-5.6 Sol84.6%GPT-5.6 Sol leads this result
Frequently asked questions
Which is better, GPT-5.6 Luna or GPT-5.6 Sol?
GPT-5.6 Sol has the higher public score, 81.48 versus 66.87, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
Which is better for coding, GPT-5.6 Luna or GPT-5.6 Sol?
GPT-5.6 Sol leads the like-for-like coding comparison across 1 shared weighted benchmark row.
Which is better for agentic tasks, GPT-5.6 Luna or GPT-5.6 Sol?
GPT-5.6 Sol leads the like-for-like agentic tasks comparison across 2 shared weighted benchmark rows.
Which costs less, GPT-5.6 Luna or GPT-5.6 Sol?
For the stated presets, chat costs $0.0008 on GPT-5.6 Luna and $0.02 on GPT-5.6 Sol; repository review costs $0.0136 and $0.34; the cache-heavy agent loop costs $0.02 and $0.5. Costs use the listed standard API rates.
Which has the larger context window, GPT-5.6 Luna or GPT-5.6 Sol?
Both models list the same context window, 1.05M.
Related comparisons
Last updated August 10, 2026
Watch GPT-5.6 Luna vs GPT-5.6 Sol
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.