Agentic
Directional only- GPT-5.6 Luna
- 84.1
- Qwen3.5-122B-A10B
- 56.4
- Weighted basis
- 2 vs 3 rows
- Reading
- Directional only
Model comparison
GPT-5.6 Luna vs Qwen3.5-122B-A10B
Updated August 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
GPT-5.6 Luna has the higher public score estimate, 66.87 versus 59.54, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
3 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.
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
No shared weighted benchmark basis supports a winner.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are 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.
19 GPT-5.6 Luna only
3 Shared
12 Qwen3.5-122B-A10B only
- Shared results
- 3
- GPT-5.6 Luna only
- 19
- Qwen3.5-122B-A10B only
- 12
- Like-for-like categories
- 0 / 8
2 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
Knowledge
Directional only- GPT-5.6 Luna
- 92.3
- Qwen3.5-122B-A10B
- 83.6
- Weighted basis
- 1 vs 3 rows
- Reading
- Directional only
Coding
Not comparable- GPT-5.6 Luna
- 62.7
- Qwen3.5-122B-A10B
- 72.0
- Weighted basis
- 1 vs 1 rows
- Reading
- Not comparable
Reasoning
Not comparable- GPT-5.6 Luna
- 59.5
- Qwen3.5-122B-A10B
- 60.2
- Weighted basis
- 1 vs 1 rows
- Reading
- Not comparable
Math
Not comparable- GPT-5.6 Luna
- 73.6
- Qwen3.5-122B-A10B
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- GPT-5.6 Luna
- Not measured
- Qwen3.5-122B-A10B
- 82.2
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Multimodal
Not comparable- GPT-5.6 Luna
- 78.4
- Qwen3.5-122B-A10B
- 77.2
- Weighted basis
- 1 vs 1 rows
- Reading
- Not comparable
Instruction following
Not comparable- GPT-5.6 Luna
- Not measured
- Qwen3.5-122B-A10B
- 93.4
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
| Category | GPT-5.6 Luna | Qwen3.5-122B-A10B | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 84.1 | 56.4 | Directional only2 vs 3 rows | Directional only |
| Knowledge | 92.3 | 83.6 | Directional only1 vs 3 rows | Directional only |
| Coding | 62.7 | 72.0 | Not comparable1 vs 1 rows | Not comparable |
| Reasoning | 59.5 | 60.2 | Not comparable1 vs 1 rows | Not comparable |
| Math | 73.6 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Multilingual | Not measured | 82.2 | Not comparable0 vs 1 rows | Not comparable |
| Multimodal | 78.4 | 77.2 | Not comparable1 vs 1 rows | Not comparable |
| Instruction following | Not measured | 93.4 | Not comparable0 vs 1 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.
Terminal-Bench 2.0
Agentic
GPT-5.6 Luna: 84.7%Qwen3.5-122B-A10B: 49.4%Normalized gap 35.3GPT-5.6 Luna source Qwen3.5-122B-A10B sourceBrowseComp
Agentic
GPT-5.6 Luna: 83.3%Qwen3.5-122B-A10B: 63.8%Normalized gap 19.5GPT-5.6 Luna source Qwen3.5-122B-A10B sourceGPQA
Knowledge
GPT-5.6 Luna: 92.3%Qwen3.5-122B-A10B: 86.6%Normalized gap 5.7GPT-5.6 Luna source Qwen3.5-122B-A10B source
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
- Qwen3.5-122B-A10B
- Self-hosted; infrastructure cost varies
- Fits in one request
Qwen3.5-122B-A10B has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- GPT-5.6 Luna
- $0.0136
- Fits in one request
- Qwen3.5-122B-A10B
- Self-hosted; infrastructure cost varies
- Fits in one request
Qwen3.5-122B-A10B has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GPT-5.6 Luna
- $0.02
- Fits in one request
- Qwen3.5-122B-A10B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
Qwen3.5-122B-A10B 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 LunaQwen3.5-122B-A10B
Context window
Maximum documented context; output-token limits may be lower.
GPT-5.6 Luna
1.05M
OpenAI model catalogQwen3.5-122B-A10B
262K
API model ID
GPT-5.6 Luna
gpt-5.6-luna
OpenAI model catalogQwen3.5-122B-A10B
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
$0.02 per 1M cached input tokens
OpenAI pricingQwen3.5-122B-A10B
No comparable hosted API rate
Documented inputs
GPT-5.6 Luna
text, image
OpenAI model catalogQwen3.5-122B-A10B
Not sourced
Documented outputs
GPT-5.6 Luna
Qwen3.5-122B-A10B
Not sourced
Provider availability
GPT-5.6 Luna
Generally Available · OpenAI Responses API
OpenAI model catalogQwen3.5-122B-A10B
Not sourced
Reasoning profile
GPT-5.6 Luna
Reasoning
Qwen3.5-122B-A10B
Reasoning
Weight access
GPT-5.6 Luna
Proprietary
Qwen3.5-122B-A10B
Open Weight
License
GPT-5.6 Luna
Proprietary
Qwen3.5-122B-A10B
Open Weight
Release date
GPT-5.6 Luna
2026-07-09
Qwen3.5-122B-A10B
2026-03-04
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, 66.87 versus 59.54, 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 evidence34 rows
Agentic
Terminal-Bench 2.0
GPT-5.6 Luna84.7%SourceQwen3.5-122B-A10B49.4%SourceGPT-5.6 Luna leads this result
BrowseComp
GPT-5.6 Luna83.3%SourceQwen3.5-122B-A10B63.8%SourceGPT-5.6 Luna leads this result
OSWorld 2.0
GPT-5.6 Luna45.6%SourceQwen3.5-122B-A10B—Not directly comparable
CyberGym
GPT-5.6 Luna77.9%SourceQwen3.5-122B-A10B—Not directly comparable
ExploitGym
GPT-5.6 Luna12.4%SourceQwen3.5-122B-A10B—Not directly comparable
Toolathlon
GPT-5.6 Luna53.4%SourceQwen3.5-122B-A10B—Not directly comparable
OSWorld-Verified
GPT-5.6 Luna—Qwen3.5-122B-A10B58%SourceNot directly comparable
Coding
SWE-bench Pro
GPT-5.6 Luna62.7%SourceQwen3.5-122B-A10B—Not directly comparable
Terminal-Bench 2.0
GPT-5.6 Luna84.7%SourceQwen3.5-122B-A10B—Not directly comparable
deepSwe
GPT-5.6 Luna67.2%SourceQwen3.5-122B-A10B—Not directly comparable
FrontierCode 1.1 Extended
GPT-5.6 Luna55.1%SourceQwen3.5-122B-A10B—Not directly comparable
cursorBench32
GPT-5.6 Luna61.1%SourceQwen3.5-122B-A10B—Not directly comparable
SWE-bench Verified
GPT-5.6 Luna—Qwen3.5-122B-A10B72%SourceNot directly comparable
Reasoning
Knowledge
GPQA
GPT-5.6 Luna92.3%SourceQwen3.5-122B-A10B86.6%SourceGPT-5.6 Luna leads this result
GPQA-D
GPT-5.6 Luna92.3%SourceQwen3.5-122B-A10B—Not directly comparable
HealthBench Professional
GPT-5.6 Luna55.7%SourceQwen3.5-122B-A10B—Not directly comparable
HealthBench Hard
GPT-5.6 Luna32.0%SourceQwen3.5-122B-A10B—Not directly comparable
MMLU-Pro
GPT-5.6 Luna—Qwen3.5-122B-A10B86.7%SourceNot directly comparable
SuperGPQA
GPT-5.6 Luna—Qwen3.5-122B-A10B67.1%SourceNot directly comparable
Math
Multilingual
MMLU-ProX
GPT-5.6 Luna—Qwen3.5-122B-A10B82.2%SourceNot directly comparable
Multimodal
MMMU-Pro
GPT-5.6 Luna78.4%SourceQwen3.5-122B-A10B—Not directly comparable
MMMU-Pro w/ Python
GPT-5.6 Luna79.5%SourceQwen3.5-122B-A10B—Not directly comparable
MMMU
GPT-5.6 Luna—Qwen3.5-122B-A10B83.9%SourceNot directly comparable
MMVU
GPT-5.6 Luna—Qwen3.5-122B-A10B74.7%SourceNot directly comparable
MathVision
GPT-5.6 Luna—Qwen3.5-122B-A10B86.2%SourceNot directly comparable
CharXiv
GPT-5.6 Luna—Qwen3.5-122B-A10B77.2%SourceNot directly comparable
V*
GPT-5.6 Luna—Qwen3.5-122B-A10B93.2%SourceNot directly comparable
Instruction following
IFEval
GPT-5.6 Luna—Qwen3.5-122B-A10B93.4%SourceNot directly comparable
Frequently asked questions
Which is better, GPT-5.6 Luna or Qwen3.5-122B-A10B?
GPT-5.6 Luna has the higher public score estimate, 66.87 versus 59.54, 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 Qwen3.5-122B-A10B?
The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.
Which is better for agentic tasks, GPT-5.6 Luna or Qwen3.5-122B-A10B?
The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which costs less, GPT-5.6 Luna or Qwen3.5-122B-A10B?
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 Qwen3.5-122B-A10B?
GPT-5.6 Luna has the larger documented context window: 1.05M, compared with 262K.
Related comparisons
Last updated August 10, 2026
Watch GPT-5.6 Luna vs Qwen3.5-122B-A10B
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.