Agentic
Directional only- Claude Sonnet 5
- 81.9
- GPT-5.3 Codex
- 71.4
- Weighted basis
- 3 vs 2 rows
- Reading
- Directional only
Claude Sonnet 5 vs GPT-5.3 Codex
Updated August 14, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
GPT-5.3 Codex has the higher public score estimate, 65.93 versus 64.78, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
4 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 Sonnet 5
Claude Sonnet 5 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-5.3 Codex 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-5.3 Codex
GPT-5.3 Codex 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.
15 Claude Sonnet 5 only
4 Shared
4 GPT-5.3 Codex only
- Shared results
- 4
- Claude Sonnet 5 only
- 15
- GPT-5.3 Codex only
- 4
- 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.
Coding
Directional only- Claude Sonnet 5
- 76.7
- GPT-5.3 Codex
- 67.2
- Weighted basis
- 2 vs 3 rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Sonnet 5
- Not measured
- GPT-5.3 Codex
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- Claude Sonnet 5
- 57.4
- GPT-5.3 Codex
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- Claude Sonnet 5
- Not measured
- GPT-5.3 Codex
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Sonnet 5
- Not measured
- GPT-5.3 Codex
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Sonnet 5
- 88.3
- GPT-5.3 Codex
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Sonnet 5
- Not measured
- GPT-5.3 Codex
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Claude Sonnet 5 | GPT-5.3 Codex | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 81.9 | 71.4 | Directional only3 vs 2 rows | Directional only |
| Coding | 76.7 | 67.2 | Directional only2 vs 3 rows | Directional only |
| Reasoning | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Knowledge | 57.4 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Math | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | 88.3 | Not measured | Not comparable1 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 Sonnet 5: 81.2%GPT-5.3 Codex: 64.7%Normalized gap 16.5Claude Sonnet 5 source GPT-5.3 Codex sourceSWE-bench Pro
Coding
Claude Sonnet 5: 63.2%GPT-5.3 Codex: 56.8%Normalized gap 6.4Claude Sonnet 5 source GPT-5.3 Codex sourceTerminal-Bench 2.0
Agentic
Claude Sonnet 5: 80.4%GPT-5.3 Codex: 77.3%Normalized gap 3.1Claude Sonnet 5 source GPT-5.3 Codex sourceSWE-bench Verified
Coding
Claude Sonnet 5: 85.2%GPT-5.3 Codex: 85%Normalized gap 0.2Claude Sonnet 5 source GPT-5.3 Codex 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 Sonnet 5
- $0.007
- Fits in one request
- GPT-5.3 Codex
- $0.00875
- 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-5.3 Codex
- $0.1295
- Fits in one request
GPT-5.3 Codex 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-5.3 Codex
- $0.525
- Fits in one request
- Cached input priced at the published list-input rate
Claude Sonnet 5 has the lower modeled cost
GPT-5.3 Codex 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-5.3 Codex
Context window
Maximum documented context; output-token limits may be lower.
Claude Sonnet 5
GPT-5.3 Codex
API model ID
Claude Sonnet 5
claude-sonnet-5
Anthropic model overviewGPT-5.3 Codex
gpt-5.3-codex
OpenAI GPT-5.3 Codex 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-5.3 Codex
Not published
Documented inputs
Claude Sonnet 5
text, image
Anthropic model overviewGPT-5.3 Codex
text, image
OpenAI model catalogDocumented outputs
Claude Sonnet 5
GPT-5.3 Codex
Provider availability
Claude Sonnet 5
Generally Available · Claude API
Anthropic model overviewGPT-5.3 Codex
Generally Available · OpenAI Responses API
OpenAI model catalogReasoning profile
Claude Sonnet 5
Reasoning
GPT-5.3 Codex
Reasoning
Weight access
Claude Sonnet 5
Proprietary
GPT-5.3 Codex
Proprietary
License
Claude Sonnet 5
Proprietary
GPT-5.3 Codex
Proprietary
Release date
Claude Sonnet 5
2026-06-30
GPT-5.3 Codex
2026-02-05
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
- GPT-5.3 Codex has the higher public score estimate, 65.93 versus 64.78, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.13 vs $0.1295. Cache-heavy agent loop: $0.18 vs $0.525.
- Context tradeoff
- Claude Sonnet 5 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 evidence23 rows
Agentic
Terminal-Bench 3.0
Claude Sonnet 514.6%SourceGPT-5.3 Codex—Not directly comparable
Terminal-Bench 2.0
Claude Sonnet 580.4%SourceGPT-5.3 Codex77.3%SourceClaude Sonnet 5 leads this result
BrowseComp
Claude Sonnet 584.7%SourceGPT-5.3 Codex—Not directly comparable
HLE w/ tools
Claude Sonnet 557.4%SourceGPT-5.3 Codex—Not directly comparable
OSWorld-Verified
Claude Sonnet 581.2%SourceGPT-5.3 Codex64.7%SourceClaude Sonnet 5 leads this result
Gert Labs
Claude Sonnet 5—GPT-5.3 Codex57.47%SourceNot directly comparable
JobBench
Claude Sonnet 5—GPT-5.3 Codex33.7%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Sonnet 585.2%SourceGPT-5.3 Codex85%SourceClaude Sonnet 5 leads this result
SWE-bench Pro
Claude Sonnet 563.2%SourceGPT-5.3 Codex56.8%SourceClaude Sonnet 5 leads this result
SWE Multilingual
Claude Sonnet 578.3%SourceGPT-5.3 Codex—Not directly comparable
SWE Multimodal
Claude Sonnet 528.1%SourceGPT-5.3 Codex—Not directly comparable
Terminal-Bench 2.0
Claude Sonnet 580.4%SourceGPT-5.3 Codex—Not directly comparable
FrontierCode 1.1 Main
Claude Sonnet 542.7%SourceGPT-5.3 Codex—Not directly comparable
cursorBench32
Claude Sonnet 561.5%SourceGPT-5.3 Codex—Not directly comparable
APEX-SWE
Claude Sonnet 546.4%SourceGPT-5.3 Codex—Not directly comparable
EEBench
Claude Sonnet 540.3%SourceGPT-5.3 Codex—Not directly comparable
3DCodeBench
Claude Sonnet 539.2%SourceGPT-5.3 Codex—Not directly comparable
SWE-Rebench
Claude Sonnet 5—GPT-5.3 Codex58.2%SourceNot directly comparable
Vibe Code Bench
Claude Sonnet 5—GPT-5.3 Codex61.77%SourceNot directly comparable
Knowledge
Multimodal
Frequently asked questions
Which is better, Claude Sonnet 5 or GPT-5.3 Codex?
GPT-5.3 Codex has the higher public score estimate, 65.93 versus 64.78, 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-5.3 Codex?
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 Sonnet 5 or GPT-5.3 Codex?
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 Sonnet 5 or GPT-5.3 Codex?
For the stated presets, chat costs $0.007 on Claude Sonnet 5 and $0.00875 on GPT-5.3 Codex; repository review costs $0.13 and $0.1295; the cache-heavy agent loop costs $0.18 and $0.525. GPT-5.3 Codex 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-5.3 Codex?
Claude Sonnet 5 has the larger documented context window: 1M, compared with 400K.
Related comparisons
Last updated August 14, 2026
Watch Claude Sonnet 5 vs GPT-5.3 Codex
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.