Updated September 24, 2026. Rank says Claude Opus 4.7 (Adaptive) 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
Claude Opus 4.7 (Adaptive) has the higher public score estimate, 68.56 versus 65.6, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 9 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Anthropic
68.56/100
Estimated · Public rank #17
90% interval 57.0–80.1
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.
Tool use, computer use, and multi-step task completion
Claude Opus 4.7 (Adaptive)
Claude Opus 4.7 (Adaptive) leads on the public agentic lane, 59.1 to 55.3, with Supported evidence for both models, although the 90% intervals overlap.
Prompts that approach the documented context limit
GPT-5.6 Luna
GPT-5.6 Luna has the larger documented context window.
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.
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. Claude Opus 4.7 (Adaptive) has no published cached-input rate, so cached tokens use its listed input rate.
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.
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Claude Opus 4.7 (Adaptive) is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
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.
Directional only · BenchAlign v5.7
GPT-5.6 Luna scores higher, but at least one score rests on Estimated evidence or a different benchmark set. Directional only, no winner.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
OSWorld 2.0Agentic
Normalized gap 27.4ARC-AGI-2Reasoning
Normalized gap 16.3BrowseCompAgentic
Normalized gap 4.0GPQAKnowledge
Normalized gap 1.9SWE-bench ProCoding
Normalized gap 1.6Each 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.
| Category | Claude Opus 4.7 (Adaptive) | GPT-5.6 Luna | Basis | Reading |
|---|---|---|---|---|
| Agentic | 59.1Supported · #19/105 | 55.3Supported · #28/105 | Like-for-likeBenchAlign v5.7 lane · 7 vs 9 public rows | Claude Opus 4.7 (Adaptive) leads · intervals overlap |
| Coding | 57.8Estimated · #20/135 | 64.5Supported · #9/135 | Directional onlyBenchAlign v5.7 lane · 3 vs 7 public rows | Directional only |
| Multimodal | 50.1#38/50 | 67.1#22/50 | Directional onlyProvisional lane · 2 vs 1 weighted rows | Directional only |
| Knowledge | 64.1Estimated · #27/158 | 64.6Supported · #22/158 | Directional onlyBenchAlign v5.7 lane · 4 vs 6 public rows | Directional only |
| Reasoning | 53.6Unranked · 3 rankable rows | 54.7#18/19 | 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 |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | 94.2Unranked · 3 rankable rows | Not comparableProvisional lane · 0 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.
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.
1K fresh input + 500 output tokens
GPT-5.6 Luna has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
GPT-5.6 Luna has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
GPT-5.6 Luna has the lower modeled cost
Claude Opus 4.7 (Adaptive) has no published cached-input rate, so cached tokens use its listed input rate.
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
Claude Opus 4.7 (Adaptive)
1M
GPT-5.6 Luna
1.05M
OpenAI model catalogClaude Opus 4.7 (Adaptive)
Not sourced
GPT-5.6 Luna
gpt-5.6-luna
OpenAI model catalogA missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Opus 4.7 (Adaptive)
Not published
GPT-5.6 Luna
$0.02 per 1M cached input tokens
OpenAI pricingClaude Opus 4.7 (Adaptive)
Not sourced
GPT-5.6 Luna
text, image
OpenAI model catalogClaude Opus 4.7 (Adaptive)
Not sourced
GPT-5.6 Luna
Claude Opus 4.7 (Adaptive)
Not sourced
GPT-5.6 Luna
Generally Available · OpenAI Responses API
OpenAI model catalogClaude Opus 4.7 (Adaptive)
Reasoning
GPT-5.6 Luna
Reasoning
Claude Opus 4.7 (Adaptive)
Proprietary
GPT-5.6 Luna
Proprietary
Claude Opus 4.7 (Adaptive)
Proprietary
GPT-5.6 Luna
Proprietary
Claude Opus 4.7 (Adaptive)
2026-04-16
GPT-5.6 Luna
2026-07-09
Claude Opus 4.7 (Adaptive) has the higher public score estimate, 68.56 versus 65.6, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
GPT-5.6 Luna scores higher for coding on the public lane, 64.5 to 57.8. Claude Opus 4.7 (Adaptive) 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.
Claude Opus 4.7 (Adaptive) leads the public agentic tasks lane, 59.1 to 55.3, with Supported evidence for both models, although the 90% intervals overlap.
For the stated presets, chat costs $0.0175 on Claude Opus 4.7 (Adaptive) and $0.0008 on GPT-5.6 Luna; repository review costs $0.325 and $0.0136; the cache-heavy agent loop costs $1.35 and $0.02. Claude Opus 4.7 (Adaptive) has no published cached-input rate, so cached tokens use its listed input rate.
GPT-5.6 Luna has the larger documented context window: 1.05M, compared with 1M.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 2.0
Not directly comparable
BrowseComp
GPT-5.6 Luna leads this result
MCP Atlas
Not directly comparable
OSWorld-Verified
Not directly comparable
CyberGym
GPT-5.6 Luna leads this result
OSWorld 2.0
GPT-5.6 Luna leads this result
JobBench
Not directly comparable
Terminal-Bench 3.0
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
ExploitGym
Not directly comparable
Toolathlon
Not directly comparable
Terminal-Bench 2.1 (Vals)
Not directly comparable
ApprenticeBench
Not directly comparable
SWE-bench Verified
Not directly comparable
SWE-bench Pro
Claude Opus 4.7 (Adaptive) leads this result
Terminal-Bench 2.0
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
DeepSWE
Not directly comparable
FrontierCode 1.1 Extended
Not directly comparable
cursorBench32
Not directly comparable
VulcanBench v3
Not directly comparable
SWE-bench (Vals)
Not directly comparable
OfficeQA Pro
Not directly comparable
CharXiv
Not directly comparable
CharXiv w/o tools
Not directly comparable
MMMU-Pro
Not directly comparable
MMMU-Pro w/ Python
Not directly comparable
GPQA
Claude Opus 4.7 (Adaptive) leads this result
GPQA-D
Claude Opus 4.7 (Adaptive) leads this result
HLE
Not directly comparable
HLE w/o tools
Not directly comparable
HealthBench Professional
Not directly comparable
HealthBench Hard
Not directly comparable
GPQA Diamond (Vals)
Not directly comparable
MMLU-Pro (Vals)
Not directly comparable
FrontierMath (legacy)
GPT-5.6 Luna leads this result
FrontierMath v2 (Tiers 1-3)
Not directly comparable
FrontierMath v2 (Tier 4)
Not directly comparable
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
