Agentic
Directional only- Claude Opus 4.8
- 80.3
- GPT-5.3 Codex
- 71.4
- Weighted basis
- 3 vs 2 rows
- Reading
- Directional only
Claude Opus 4.8 vs GPT-5.3 Codex
Updated August 26, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Claude Opus 4.8 has the higher public score, 76.45 versus 66.01, and the 90% score intervals do not overlap.
5 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 4.8
Claude Opus 4.8 has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 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
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
GPT-5.3 Codex
GPT-5.3 Codex has the lower estimated token cost for this stated workload. Claude Opus 4.8 has no published cached-input rate, so cached tokens use its listed input rate. 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.
28 Claude Opus 4.8 only
5 Shared
3 GPT-5.3 Codex only
- Shared results
- 5
- Claude Opus 4.8 only
- 28
- GPT-5.3 Codex only
- 3
- 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 Opus 4.8
- 81.1
- GPT-5.3 Codex
- 67.2
- Weighted basis
- 2 vs 3 rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Opus 4.8
- 72.1
- GPT-5.3 Codex
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- Claude Opus 4.8
- 62.7
- GPT-5.3 Codex
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- Claude Opus 4.8
- 53.9
- GPT-5.3 Codex
- Not measured
- Weighted basis
- 3 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 4.8
- Not measured
- GPT-5.3 Codex
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Opus 4.8
- 77.0
- GPT-5.3 Codex
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Opus 4.8
- Not measured
- GPT-5.3 Codex
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Claude Opus 4.8 | GPT-5.3 Codex | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 80.3 | 71.4 | Directional only3 vs 2 rows | Directional only |
| Coding | 81.1 | 67.2 | Directional only2 vs 3 rows | Directional only |
| Reasoning | 72.1 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Knowledge | 62.7 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Math | 53.9 | Not measured | Not comparable3 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | 77.0 | Not measured | Not comparable2 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 4.8: 83.4%GPT-5.3 Codex: 64.7%Normalized gap 18.7Claude Opus 4.8 source GPT-5.3 Codex sourceSWE-bench Pro
Coding
Claude Opus 4.8: 69.2%GPT-5.3 Codex: 56.8%Normalized gap 12.4Claude Opus 4.8 source GPT-5.3 Codex sourceSWE-bench Verified
Coding
Claude Opus 4.8: 88.6%GPT-5.3 Codex: 85%Normalized gap 3.6Claude Opus 4.8 source GPT-5.3 Codex sourceTerminal-Bench 2.0
Agentic
Claude Opus 4.8: 74.6%GPT-5.3 Codex: 77.3%Normalized gap 2.7Claude Opus 4.8 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 Opus 4.8
- $0.0175
- Fits in one request
- GPT-5.3 Codex
- $0.00875
- Fits in one request
GPT-5.3 Codex has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Opus 4.8
- $0.325
- 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 Opus 4.8
- $1.35
- Fits in one request
- Cached input priced at the published list-input rate
- GPT-5.3 Codex
- $0.525
- Fits in one request
- Cached input priced at the published list-input rate
GPT-5.3 Codex has the lower modeled cost
Claude Opus 4.8 has no published cached-input rate, so cached tokens use its listed input rate. 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 Opus 4.8GPT-5.3 Codex
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 4.8
GPT-5.3 Codex
API model ID
Claude Opus 4.8
claude-opus-4-8
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 Opus 4.8
Not published
GPT-5.3 Codex
Not published
Documented inputs
Claude Opus 4.8
text, image
Anthropic model overviewGPT-5.3 Codex
text, image
OpenAI model catalogDocumented outputs
Claude Opus 4.8
GPT-5.3 Codex
Provider availability
Claude Opus 4.8
Generally Available · Claude API
Anthropic model overviewGPT-5.3 Codex
Generally Available · OpenAI Responses API
OpenAI model catalogReasoning profile
Claude Opus 4.8
Reasoning
GPT-5.3 Codex
Reasoning
Weight access
Claude Opus 4.8
Proprietary
GPT-5.3 Codex
Proprietary
License
Claude Opus 4.8
Proprietary
GPT-5.3 Codex
Proprietary
Release date
Claude Opus 4.8
2026-05-28
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
- Claude Opus 4.8 has the higher public score, 76.45 versus 66.01, and the 90% score intervals do not overlap.
- Workload cost
- Repository review: $0.325 vs $0.1295. Cache-heavy agent loop: $1.35 vs $0.525.
- Context tradeoff
- Claude Opus 4.8 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 evidence36 rows
Agentic
Terminal-Bench 3.0
Claude Opus 4.821.1%SourceGPT-5.3 Codex—Not directly comparable
Terminal-Bench 2.0
Claude Opus 4.874.6%SourceGPT-5.3 Codex77.3%SourceGPT-5.3 Codex leads this result
BrowseComp
Claude Opus 4.884.3%SourceGPT-5.3 Codex—Not directly comparable
DeepSearchQA
Claude Opus 4.893.1%SourceGPT-5.3 Codex—Not directly comparable
OSWorld-Verified
Claude Opus 4.883.4%SourceGPT-5.3 Codex64.7%SourceClaude Opus 4.8 leads this result
Finance Agent v2
Claude Opus 4.853.9%SourceGPT-5.3 Codex—Not directly comparable
MCP Atlas
Claude Opus 4.882.2%SourceGPT-5.3 Codex—Not directly comparable
Toolathlon
Claude Opus 4.859.9%SourceGPT-5.3 Codex—Not directly comparable
Gert Labs
Shared sourceClaude Opus 4.872.97%GPT-5.3 Codex57.47%Claude Opus 4.8 leads this result
ResearchClawBench
Claude Opus 4.821.1%SourceGPT-5.3 Codex—Not directly comparable
OSWorld 2.0
Claude Opus 4.820.6%SourceGPT-5.3 Codex—Not directly comparable
JobBench
Claude Opus 4.8—GPT-5.3 Codex33.7%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Opus 4.888.6%SourceGPT-5.3 Codex85%SourceClaude Opus 4.8 leads this result
SWE-bench Pro
Claude Opus 4.869.2%SourceGPT-5.3 Codex56.8%SourceClaude Opus 4.8 leads this result
SWE Multilingual
Claude Opus 4.884.4%SourceGPT-5.3 Codex—Not directly comparable
SWE Multimodal
Claude Opus 4.838.4%SourceGPT-5.3 Codex—Not directly comparable
Terminal-Bench 2.0
Claude Opus 4.874.6%SourceGPT-5.3 Codex—Not directly comparable
cursorBench31
Claude Opus 4.858.4%SourceGPT-5.3 Codex—Not directly comparable
cursorBench32
Claude Opus 4.862.3%SourceGPT-5.3 Codex—Not directly comparable
FrontierCode 1.1 Main
Claude Opus 4.846.5%SourceGPT-5.3 Codex—Not directly comparable
SWE-Rebench
Claude Opus 4.8—GPT-5.3 Codex58.2%SourceNot directly comparable
Vibe Code Bench
Claude Opus 4.8—GPT-5.3 Codex61.77%SourceNot directly comparable
Reasoning
Knowledge
Math
Multilingual
INCLUDE
Claude Opus 4.887.6%SourceGPT-5.3 Codex—Not directly comparable
Multimodal
OfficeQA Pro
Claude Opus 4.866.2%SourceGPT-5.3 Codex—Not directly comparable
ScreenSpot Pro
Claude Opus 4.887.9%SourceGPT-5.3 Codex—Not directly comparable
CharXiv
Claude Opus 4.889.9%SourceGPT-5.3 Codex—Not directly comparable
CharXiv w/o tools
Claude Opus 4.880.5%SourceGPT-5.3 Codex—Not directly comparable
Frequently asked questions
Which is better, Claude Opus 4.8 or GPT-5.3 Codex?
Claude Opus 4.8 has the higher public score, 76.45 versus 66.01, 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 Opus 4.8 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 Opus 4.8 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 Opus 4.8 or GPT-5.3 Codex?
For the stated presets, chat costs $0.0175 on Claude Opus 4.8 and $0.00875 on GPT-5.3 Codex; repository review costs $0.325 and $0.1295; the cache-heavy agent loop costs $1.35 and $0.525. Claude Opus 4.8 has no published cached-input rate, so cached tokens use its listed input rate. 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 Opus 4.8 or GPT-5.3 Codex?
Claude Opus 4.8 has the larger documented context window: 1M, compared with 400K.
Related comparisons
Last updated August 26, 2026
Watch Claude Opus 4.8 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.