Math
Like-for-like- Claude Opus 4.6
- 36.3
- GPT-5.4 nano
- 21.0
- Weighted basis
- 2 vs 2 rows
- Reading
- Claude Opus 4.6 leads
Model comparison
Claude Opus 4.6 vs GPT-5.4 nano
Updated July 30, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Claude Opus 4.6 has the higher public score estimate, 67.76 versus 65.98, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
9 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
Claude Opus 4.6
Claude Opus 4.6 has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
GPT-5.4 nano
GPT-5.4 nano 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-5.4 nano
GPT-5.4 nano has the lower estimated token cost for this stated workload. Claude Opus 4.6 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
GPT-5.4 nano
GPT-5.4 nano 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
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
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
24 Claude Opus 4.6 only
9 Shared
4 GPT-5.4 nano only
- Shared results
- 9
- Claude Opus 4.6 only
- 24
- GPT-5.4 nano only
- 4
- Like-for-like categories
- 2 / 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.
Multimodal
Like-for-like- Claude Opus 4.6
- 77.3
- GPT-5.4 nano
- 66.1
- Weighted basis
- 1 vs 1 rows
- Reading
- Claude Opus 4.6 leads
Agentic
Directional only- Claude Opus 4.6
- 73.0
- GPT-5.4 nano
- 42.9
- Weighted basis
- 3 vs 2 rows
- Reading
- Directional only
Knowledge
Directional only- Claude Opus 4.6
- 69.1
- GPT-5.4 nano
- 43.8
- Weighted basis
- 4 vs 2 rows
- Reading
- Directional only
Coding
Not comparable- Claude Opus 4.6
- 68.1
- GPT-5.4 nano
- Not measured
- Weighted basis
- 3 vs 0 rows
- Reading
- Not comparable
Reasoning
Not comparable- Claude Opus 4.6
- Not measured
- GPT-5.4 nano
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 4.6
- Not measured
- GPT-5.4 nano
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Opus 4.6
- Not measured
- GPT-5.4 nano
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Claude Opus 4.6 | GPT-5.4 nano | Weighted basis | Reading |
|---|---|---|---|---|
| Math | 36.3 | 21.0 | Like-for-like2 vs 2 rows | Claude Opus 4.6 leads |
| Multimodal | 77.3 | 66.1 | Like-for-like1 vs 1 rows | Claude Opus 4.6 leads |
| Agentic | 73.0 | 42.9 | Directional only3 vs 2 rows | Directional only |
| Knowledge | 69.1 | 43.8 | Directional only4 vs 2 rows | Directional only |
| Coding | 68.1 | Not measured | Not comparable3 vs 0 rows | Not comparable |
| Reasoning | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| 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.
OSWorld-Verified
Agentic
Claude Opus 4.6: 72.7%GPT-5.4 nano: 39%Normalized gap 33.7Claude Opus 4.6 source GPT-5.4 nano sourceTerminal-Bench 2.0
Agentic
Claude Opus 4.6: 65.4%GPT-5.4 nano: 46.3%Normalized gap 19.1Claude Opus 4.6 source GPT-5.4 nano sourceFrontierMath v2 (Tier 4)
Math
HLE
Knowledge
Claude Opus 4.6: 53%GPT-5.4 nano: 37.7%Normalized gap 15.3Claude Opus 4.6 source GPT-5.4 nano sourceFrontierMath v2 (Tiers 1-3)
Math
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 Opus 4.6
- $0.0175
- Fits in one request
- GPT-5.4 nano
- $0.00082
- Fits in one request
GPT-5.4 nano has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Opus 4.6
- $0.325
- Fits in one request
- GPT-5.4 nano
- $0.01375
- Fits in one request
GPT-5.4 nano 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 Opus 4.6
- $1.35
- Fits in one request
- Cached input priced at the published list-input rate
- GPT-5.4 nano
- $0.0205
- Fits in one request
GPT-5.4 nano has the lower modeled cost
Claude Opus 4.6 has no published cached-input rate, so cached tokens use its listed input rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Opus 4.6GPT-5.4 nano
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 4.6
1M
GPT-5.4 nano
API model ID
Claude Opus 4.6
Not sourced
GPT-5.4 nano
gpt-5.4-nano
OpenAI GPT-5.4 nano model documentationCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Opus 4.6
Not published
GPT-5.4 nano
$0.02 per 1M cached input tokens
OpenAI pricingDocumented inputs
Claude Opus 4.6
Not sourced
GPT-5.4 nano
text, image
OpenAI model catalogDocumented outputs
Claude Opus 4.6
Not sourced
GPT-5.4 nano
Provider availability
Claude Opus 4.6
Not sourced
GPT-5.4 nano
Generally Available · OpenAI Responses API
OpenAI model catalogReasoning profile
Claude Opus 4.6
Non-Reasoning
GPT-5.4 nano
Reasoning
Weight access
Claude Opus 4.6
Proprietary
GPT-5.4 nano
Proprietary
License
Claude Opus 4.6
Proprietary
GPT-5.4 nano
Proprietary
Release date
Claude Opus 4.6
2026-02-01
GPT-5.4 nano
2026-03-17
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 Opus 4.6 has the higher public score estimate, 67.76 versus 65.98, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.325 vs $0.01375. Cache-heavy agent loop: $1.35 vs $0.0205.
- Context tradeoff
- Claude Opus 4.6 has the larger documented window (1M).
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 evidence37 rows
Agentic
Terminal-Bench 2.0
Claude Opus 4.665.4%SourceGPT-5.4 nano46.3%SourceClaude Opus 4.6 leads this result
BrowseComp
Claude Opus 4.683.7%SourceGPT-5.4 nano—Not directly comparable
OSWorld-Verified
Claude Opus 4.672.7%SourceGPT-5.4 nano39%SourceClaude Opus 4.6 leads this result
Claw-Eval
Claude Opus 4.670.4%SourceGPT-5.4 nano—Not directly comparable
DeepSearchQA
Claude Opus 4.673.7%SourceGPT-5.4 nano—Not directly comparable
CyberGym
Claude Opus 4.666.6%SourceGPT-5.4 nano—Not directly comparable
Gert Labs
Claude Opus 4.661.85%SourceGPT-5.4 nano—Not directly comparable
ResearchClawBench
Claude Opus 4.619.9%SourceGPT-5.4 nano—Not directly comparable
JobBench
Claude Opus 4.636.7%SourceGPT-5.4 nano—Not directly comparable
MCP Atlas
Claude Opus 4.6—GPT-5.4 nano56.1%SourceNot directly comparable
Toolathlon
Claude Opus 4.6—GPT-5.4 nano35.5%SourceNot directly comparable
τ²-bench results
Claude Opus 4.6—GPT-5.4 nano92.5%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Opus 4.680.8%SourceGPT-5.4 nano—Not directly comparable
SWE-bench Verified*
Claude Opus 4.675.6%SourceGPT-5.4 nano—Not directly comparable
LiveCodeBench Pro
Claude Opus 4.670.7%SourceGPT-5.4 nano—Not directly comparable
SWE-bench Pro
Claude Opus 4.653.4%SourceGPT-5.4 nano—Not directly comparable
SWE-Rebench
Claude Opus 4.665.3%SourceGPT-5.4 nano—Not directly comparable
React Native Evals
Claude Opus 4.684.1%SourceGPT-5.4 nano—Not directly comparable
Vibe Code Bench
Shared sourceClaude Opus 4.657.57%GPT-5.4 nano26.10%Claude Opus 4.6 leads this result
FrontierCode 1.1 Main
Claude Opus 4.626.9%SourceGPT-5.4 nano—Not directly comparable
Knowledge
GPQA
Claude Opus 4.691.3%SourceGPT-5.4 nano82.8%SourceClaude Opus 4.6 leads this result
GPQA-D
Claude Opus 4.689.2%SourceGPT-5.4 nano—Not directly comparable
SuperGPQA
Claude Opus 4.695%SourceGPT-5.4 nano—Not directly comparable
MMLU-Pro
Claude Opus 4.682%SourceGPT-5.4 nano—Not directly comparable
MMLU-Pro (Arcee)
Claude Opus 4.689.1%SourceGPT-5.4 nano—Not directly comparable
HLE
Claude Opus 4.653%SourceGPT-5.4 nano37.7%SourceClaude Opus 4.6 leads this result
HLE w/o tools
Claude Opus 4.640%SourceGPT-5.4 nano24.3%SourceClaude Opus 4.6 leads this result
HealthBench Hard
Claude Opus 4.614.8%SourceGPT-5.4 nano—Not directly comparable
MedXpertQA (Text)
Claude Opus 4.652.1%SourceGPT-5.4 nano—Not directly comparable
Math
AIME25 (Arcee)
Claude Opus 4.699.8%SourceGPT-5.4 nano—Not directly comparable
FrontierMath v2 (Tiers 1-3)
Shared sourceClaude Opus 4.640.700%GPT-5.4 nano25.860%Claude Opus 4.6 leads this result
FrontierMath v2 (Tier 4)
Shared sourceClaude Opus 4.622.900%GPT-5.4 nano6.250%Claude Opus 4.6 leads this result
Multimodal
MMMU-Pro
Claude Opus 4.677.3%SourceGPT-5.4 nano66.1%SourceClaude Opus 4.6 leads this result
ERQA
Claude Opus 4.651.6%SourceGPT-5.4 nano—Not directly comparable
ScreenSpot Pro
Claude Opus 4.683.1%SourceGPT-5.4 nano—Not directly comparable
MedXpertQA (MM)
Claude Opus 4.664.8%SourceGPT-5.4 nano—Not directly comparable
MMMU-Pro w/ Python
Claude Opus 4.6—GPT-5.4 nano69.5%SourceNot directly comparable
Frequently asked questions
Which is better, Claude Opus 4.6 or GPT-5.4 nano?
Claude Opus 4.6 has the higher public score estimate, 67.76 versus 65.98, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Claude Opus 4.6 or GPT-5.4 nano?
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, Claude Opus 4.6 or GPT-5.4 nano?
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 Opus 4.6 or GPT-5.4 nano?
For the stated presets, chat costs $0.0175 on Claude Opus 4.6 and $0.00082 on GPT-5.4 nano; repository review costs $0.325 and $0.01375; the cache-heavy agent loop costs $1.35 and $0.0205. Claude Opus 4.6 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Opus 4.6 or GPT-5.4 nano?
Claude Opus 4.6 has the larger documented context window: 1M, compared with 400K.
Related comparisons
Last updated July 30, 2026
Watch Claude Opus 4.6 vs GPT-5.4 nano
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.