Agentic
Directional only- Claude Mythos 5
- 87.0
- GPT-5.6 Luna
- 84.1
- Weighted basis
- 3 vs 2 rows
- Reading
- Directional only
Model comparison
Claude Mythos 5 vs GPT-5.6 Luna
Updated August 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Claude Mythos 5 has the higher public score, 83.04 versus 66.87, and the 90% score intervals do not overlap.
6 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
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
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
Show secondary and unsupported calls
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
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
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
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
9 Claude Mythos 5 only
6 Shared
16 GPT-5.6 Luna only
- Shared results
- 6
- Claude Mythos 5 only
- 9
- GPT-5.6 Luna only
- 16
- Like-for-like categories
- 0 / 8
3 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.
Coding
Directional only- Claude Mythos 5
- 89.7
- GPT-5.6 Luna
- 62.7
- Weighted basis
- 2 vs 1 rows
- Reading
- Directional only
Knowledge
Directional only- Claude Mythos 5
- 68.5
- GPT-5.6 Luna
- 92.3
- Weighted basis
- 2 vs 1 rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Mythos 5
- Not measured
- GPT-5.6 Luna
- 59.5
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Math
Not comparable- Claude Mythos 5
- 97.6
- GPT-5.6 Luna
- 73.6
- Weighted basis
- 1 vs 2 rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Mythos 5
- Not measured
- GPT-5.6 Luna
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Mythos 5
- 93.5
- GPT-5.6 Luna
- 78.4
- Weighted basis
- 1 vs 1 rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Mythos 5
- Not measured
- GPT-5.6 Luna
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Claude Mythos 5 | GPT-5.6 Luna | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 87.0 | 84.1 | Directional only3 vs 2 rows | Directional only |
| Coding | 89.7 | 62.7 | Directional only2 vs 1 rows | Directional only |
| Knowledge | 68.5 | 92.3 | Directional only2 vs 1 rows | Directional only |
| Reasoning | Not measured | 59.5 | Not comparable0 vs 1 rows | Not comparable |
| Math | 97.6 | 73.6 | Not comparable1 vs 2 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | 93.5 | 78.4 | Not comparable1 vs 1 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.
SWE-bench Pro
Coding
Claude Mythos 5: 80.3%GPT-5.6 Luna: 62.7%Normalized gap 17.6Claude Mythos 5 source GPT-5.6 Luna sourceBrowseComp
Agentic
Terminal-Bench 2.0
Agentic
GPQA
Knowledge
Claude Mythos 5: 94.1%GPT-5.6 Luna: 92.3%Normalized gap 1.8Claude Mythos 5 source GPT-5.6 Luna 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
- Claude Mythos 5
- $0.035
- 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
- Claude Mythos 5
- $0.65
- 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
- Claude Mythos 5
- $0.9
- 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.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Mythos 5GPT-5.6 Luna
Context window
Maximum documented context; output-token limits may be lower.
Claude Mythos 5
GPT-5.6 Luna
1.05M
OpenAI model catalogAPI model ID
Claude Mythos 5
claude-mythos-5
Anthropic model overviewGPT-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.
Claude Mythos 5
$1 per 1M cached input tokens
Claude API pricingGPT-5.6 Luna
$0.02 per 1M cached input tokens
OpenAI pricingDocumented inputs
Claude Mythos 5
text, image
Anthropic model overviewGPT-5.6 Luna
text, image
OpenAI model catalogDocumented outputs
Claude Mythos 5
GPT-5.6 Luna
Provider availability
Claude Mythos 5
Limited Access · Claude API
Anthropic model overviewGPT-5.6 Luna
Generally Available · OpenAI Responses API
OpenAI model catalogReasoning profile
Claude Mythos 5
Reasoning
GPT-5.6 Luna
Reasoning
Weight access
Claude Mythos 5
Proprietary
GPT-5.6 Luna
Proprietary
License
Claude Mythos 5
Proprietary
GPT-5.6 Luna
Proprietary
Release date
Claude Mythos 5
2026-06-09
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
- Claude Mythos 5 has the higher public score, 83.04 versus 66.87, and the 90% score intervals do not overlap.
- Workload cost
- Repository review: $0.65 vs $0.0136. Cache-heavy agent loop: $0.9 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.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence31 rows
Agentic
Terminal-Bench 2.0
Claude Mythos 588%SourceGPT-5.6 Luna84.7%SourceClaude Mythos 5 leads this result
OSWorld-Verified
Claude Mythos 585%SourceGPT-5.6 Luna—Not directly comparable
BrowseComp
Claude Mythos 588%SourceGPT-5.6 Luna83.3%SourceClaude Mythos 5 leads this result
ExploitGym
Claude Mythos 517.5%SourceGPT-5.6 Luna12.4%SourceClaude Mythos 5 leads this result
OSWorld 2.0
Claude Mythos 5—GPT-5.6 Luna45.6%SourceNot directly comparable
CyberGym
Claude Mythos 5—GPT-5.6 Luna77.9%SourceNot directly comparable
Toolathlon
Claude Mythos 5—GPT-5.6 Luna53.4%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Mythos 595.5%SourceGPT-5.6 Luna—Not directly comparable
SWE-bench Pro
Claude Mythos 580.3%SourceGPT-5.6 Luna62.7%SourceClaude Mythos 5 leads this result
Terminal-Bench 2.0
Claude Mythos 588.0%SourceGPT-5.6 Luna84.7%SourceClaude Mythos 5 leads this result
deepSwe
Claude Mythos 5—GPT-5.6 Luna67.2%SourceNot directly comparable
FrontierCode 1.1 Extended
Claude Mythos 5—GPT-5.6 Luna55.1%SourceNot directly comparable
cursorBench32
Claude Mythos 5—GPT-5.6 Luna61.1%SourceNot directly comparable
Reasoning
Knowledge
GPQA
Claude Mythos 594.1%SourceGPT-5.6 Luna92.3%SourceClaude Mythos 5 leads this result
HLE
Claude Mythos 564.5%SourceGPT-5.6 Luna—Not directly comparable
HLE w/o tools
Claude Mythos 559%SourceGPT-5.6 Luna—Not directly comparable
GPQA-D
Claude Mythos 5—GPT-5.6 Luna92.3%SourceNot directly comparable
HealthBench Professional
Claude Mythos 5—GPT-5.6 Luna55.7%SourceNot directly comparable
HealthBench Hard
Claude Mythos 5—GPT-5.6 Luna32.0%SourceNot directly comparable
Math
USAMO 2026
Claude Mythos 597.6%SourceGPT-5.6 Luna—Not directly comparable
FrontierMath (legacy)
Claude Mythos 5—GPT-5.6 Luna78.6%SourceNot directly comparable
FrontierMath v2 (Tiers 1-3)
Claude Mythos 5—GPT-5.6 Luna78.600%SourceNot directly comparable
FrontierMath v2 (Tier 4)
Claude Mythos 5—GPT-5.6 Luna58.500%SourceNot directly comparable
Multilingual
SWE Multilingual
Claude Mythos 592.2%SourceGPT-5.6 Luna—Not directly comparable
Multimodal
SWE-bench Multimodal
Claude Mythos 554.9%SourceGPT-5.6 Luna—Not directly comparable
CharXiv
Claude Mythos 593.5%SourceGPT-5.6 Luna—Not directly comparable
CharXiv w/o tools
Claude Mythos 588.9%SourceGPT-5.6 Luna—Not directly comparable
MMMU-Pro
Claude Mythos 5—GPT-5.6 Luna78.4%SourceNot directly comparable
MMMU-Pro w/ Python
Claude Mythos 5—GPT-5.6 Luna79.5%SourceNot directly comparable
Frequently asked questions
Which is better, Claude Mythos 5 or GPT-5.6 Luna?
Claude Mythos 5 has the higher public score, 83.04 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, Claude Mythos 5 or GPT-5.6 Luna?
The current coding 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 is better for agentic tasks, Claude Mythos 5 or GPT-5.6 Luna?
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, Claude Mythos 5 or GPT-5.6 Luna?
For the stated presets, chat costs $0.035 on Claude Mythos 5 and $0.0008 on GPT-5.6 Luna; repository review costs $0.65 and $0.0136; the cache-heavy agent loop costs $0.9 and $0.02. Costs use the listed standard API rates.
Which has the larger context window, Claude Mythos 5 or GPT-5.6 Luna?
GPT-5.6 Luna has the larger documented context window: 1.05M, compared with 1M.
Related comparisons
Last updated August 10, 2026
Watch Claude Mythos 5 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.