Agentic
Directional only- Claude Sonnet 5
- 65.9
- Supported · #11/153
- GPT-5.4 Pro
- 56.0
- Estimated · #36/153
- Basis
- BenchAlign lane · 7 vs 1 public rows
- Reading
- Directional only
Claude Sonnet 5 vs GPT-5.4 Pro
Updated September 14, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Claude Sonnet 5 has the higher public score estimate, 69.92 versus 60.15, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
3 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
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-5.4 Pro
GPT-5.4 Pro has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Claude Sonnet 5
Claude Sonnet 5 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
Claude Sonnet 5
Claude Sonnet 5 has the lower estimated token cost for this stated workload. GPT-5.4 Pro 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
Claude Sonnet 5
Claude Sonnet 5 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
GPT-5.4 Pro is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
GPT-5.4 Pro is scored on Estimated evidence for agentic, so the reading is 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.
23 Claude Sonnet 5 only
3 Shared
7 GPT-5.4 Pro only
- Shared results
- 3
- Claude Sonnet 5 only
- 23
- GPT-5.4 Pro only
- 7
- Like-for-like categories
- 0 / 8
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign 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.
Knowledge
Directional only- Claude Sonnet 5
- 66.6
- Supported · #20/183
- GPT-5.4 Pro
- 58.6
- Estimated · #40/183
- Basis
- BenchAlign lane · 6 vs 4 public rows
- Reading
- Directional only
Coding
Not comparable- Claude Sonnet 5
- 64.1
- Supported · #13/152
- GPT-5.4 Pro
- Not ranked
- Basis
- BenchAlign lane · 11 vs 0 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Claude Sonnet 5
- 77.4
- Unranked · 2 rankable rows
- GPT-5.4 Pro
- 70.1
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Sonnet 5
- Not ranked
- GPT-5.4 Pro
- 69.0
- Unranked · 4 rankable rows
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Sonnet 5
- Not ranked
- GPT-5.4 Pro
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Sonnet 5
- 77.5
- #13/48
- GPT-5.4 Pro
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Sonnet 5
- Not ranked
- GPT-5.4 Pro
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Sonnet 5 | GPT-5.4 Pro | Basis | Reading |
|---|---|---|---|---|
| Agentic | 65.9Supported · #11/153 | 56.0Estimated · #36/153 | Directional onlyBenchAlign lane · 7 vs 1 public rows | Directional only |
| Knowledge | 66.6Supported · #20/183 | 58.6Estimated · #40/183 | Directional onlyBenchAlign lane · 6 vs 4 public rows | Directional only |
| Coding | 64.1Supported · #13/152 | Not ranked | Not comparableBenchAlign lane · 11 vs 0 public rows | Not comparable |
| Reasoning | 77.4Unranked · 2 rankable rows | 70.1Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Math | Not ranked | 69.0Unranked · 4 rankable rows | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 77.5#13/48 | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
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.
BrowseComp
Agentic
HLE
Knowledge
HLE w/o tools
Knowledge
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 Sonnet 5
- $0.007
- Fits in one request
- GPT-5.4 Pro
- $0.12
- Fits in one request
Claude Sonnet 5 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Sonnet 5
- $0.13
- Fits in one request
- GPT-5.4 Pro
- $2.04
- Fits in one request
Claude Sonnet 5 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 Sonnet 5
- $0.18
- Fits in one request
- GPT-5.4 Pro
- $8.40
- Fits in one request
- Cached input priced at the published list-input rate
Claude Sonnet 5 has the lower modeled cost
GPT-5.4 Pro 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 Sonnet 5GPT-5.4 Pro
Context window
Maximum documented context; output-token limits may be lower.
Claude Sonnet 5
GPT-5.4 Pro
API model ID
Claude Sonnet 5
claude-sonnet-5
Anthropic model overviewGPT-5.4 Pro
gpt-5.4-pro
OpenAI GPT-5.4 Pro model documentationCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Sonnet 5
$0.2 per 1M cached input tokens
Claude API pricingGPT-5.4 Pro
Not published
OpenAI pricingDocumented inputs
Claude Sonnet 5
text, image
Anthropic model overviewGPT-5.4 Pro
text, image
OpenAI model catalogDocumented outputs
Claude Sonnet 5
GPT-5.4 Pro
Provider availability
Claude Sonnet 5
Generally Available · Claude API
Anthropic model overviewGPT-5.4 Pro
Generally Available · OpenAI Responses API
OpenAI model catalogReasoning profile
Claude Sonnet 5
Reasoning
GPT-5.4 Pro
Reasoning
Weight access
Claude Sonnet 5
Proprietary
GPT-5.4 Pro
Proprietary
License
Claude Sonnet 5
Proprietary
GPT-5.4 Pro
Proprietary
Release date
Claude Sonnet 5
2026-06-30
GPT-5.4 Pro
2026-03-05
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 Sonnet 5 has the higher public score estimate, 69.92 versus 60.15, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.13 vs $2.04. Cache-heavy agent loop: $0.18 vs $8.40.
- Context tradeoff
- GPT-5.4 Pro 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 evidence33 rows
Agentic
Terminal-Bench 3.0
Claude Sonnet 514.6%SourceGPT-5.4 Pro—Not directly comparable
Terminal-Bench 2.0
Claude Sonnet 580.4%SourceGPT-5.4 Pro—Not directly comparable
BrowseComp
Claude Sonnet 584.7%SourceGPT-5.4 Pro89.3%SourceGPT-5.4 Pro leads this result
HLE w/ tools
Claude Sonnet 557.4%SourceGPT-5.4 Pro—Not directly comparable
OSWorld-Verified
Claude Sonnet 581.2%SourceGPT-5.4 Pro—Not directly comparable
Terminal-Bench 2.1 (Vals)
Claude Sonnet 574.5%SourceGPT-5.4 Pro—Not directly comparable
ApprenticeBench
Claude Sonnet 516%SourceGPT-5.4 Pro—Not directly comparable
Coding
SWE-bench Verified
Claude Sonnet 585.2%SourceGPT-5.4 Pro—Not directly comparable
SWE-bench Pro
Claude Sonnet 563.2%SourceGPT-5.4 Pro—Not directly comparable
SWE Multilingual
Claude Sonnet 578.3%SourceGPT-5.4 Pro—Not directly comparable
SWE Multimodal
Claude Sonnet 528.1%SourceGPT-5.4 Pro—Not directly comparable
Terminal-Bench 2.0
Claude Sonnet 580.4%SourceGPT-5.4 Pro—Not directly comparable
FrontierCode 1.1 Main
Claude Sonnet 542.7%SourceGPT-5.4 Pro—Not directly comparable
cursorBench32
Claude Sonnet 561.5%SourceGPT-5.4 Pro—Not directly comparable
VulcanBench CII v1
Claude Sonnet 589.2%SourceGPT-5.4 Pro—Not directly comparable
LiveCodeBench (Vals)
Claude Sonnet 582.4%SourceGPT-5.4 Pro—Not directly comparable
SWE-bench (Vals)
Claude Sonnet 579.6%SourceGPT-5.4 Pro—Not directly comparable
cursorBench40
Claude Sonnet 534.1%SourceGPT-5.4 Pro—Not directly comparable
Reasoning
ARC-AGI-2
Claude Sonnet 5—GPT-5.4 Pro83.3%SourceNot directly comparable
Knowledge
HLE
Claude Sonnet 557.4%SourceGPT-5.4 Pro58.7%SourceGPT-5.4 Pro leads this result
HLE w/o tools
Claude Sonnet 543.2%SourceGPT-5.4 Pro42.7%SourceClaude Sonnet 5 leads this result
HLE-Verified
Claude Sonnet 531.0%SourceGPT-5.4 Pro—Not directly comparable
LABBench2
Claude Sonnet 580.1%SourceGPT-5.4 Pro—Not directly comparable
GPQA Diamond (Vals)
Claude Sonnet 588.9%SourceGPT-5.4 Pro—Not directly comparable
MMLU-Pro (Vals)
Claude Sonnet 587.5%SourceGPT-5.4 Pro—Not directly comparable
FrontierScience
Claude Sonnet 5—GPT-5.4 Pro36.7%SourceNot directly comparable
FrontierScience Research
Claude Sonnet 5—GPT-5.4 Pro36.7%SourceNot directly comparable
Math
IPhO 2025 (Theory)
Claude Sonnet 5—GPT-5.4 Pro93.5%SourceNot directly comparable
FrontierMath (legacy)
Claude Sonnet 5—GPT-5.4 Pro50%SourceNot directly comparable
FrontierMath v2 (Tiers 1-3)
Claude Sonnet 5—GPT-5.4 Pro50.000%SourceNot directly comparable
FrontierMath v2 (Tier 4)
Claude Sonnet 5—GPT-5.4 Pro37.500%SourceNot directly comparable
Multimodal
Frequently asked questions
Which is better, Claude Sonnet 5 or GPT-5.4 Pro?
Claude Sonnet 5 has the higher public score estimate, 69.92 versus 60.15, 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 Sonnet 5 or GPT-5.4 Pro?
GPT-5.4 Pro is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, Claude Sonnet 5 or GPT-5.4 Pro?
Claude Sonnet 5 scores higher for agentic tasks on the public lane, 65.9 to 56. GPT-5.4 Pro is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which costs less, Claude Sonnet 5 or GPT-5.4 Pro?
For the stated presets, chat costs $0.007 on Claude Sonnet 5 and $0.12 on GPT-5.4 Pro; repository review costs $0.13 and $2.04; the cache-heavy agent loop costs $0.18 and $8.40. GPT-5.4 Pro has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Sonnet 5 or GPT-5.4 Pro?
GPT-5.4 Pro has the larger documented context window: 1.05M, compared with 1M.
Related comparisons
Last updated September 14, 2026
Watch Claude Sonnet 5 vs GPT-5.4 Pro
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.