Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start the free Radar Brief
BenchLM
Anthropic logo
Model A
Claude Opus 4.7

Anthropic

72.33/100

Supported · Public rank #17

90% interval 60.4–84.3

Claude Opus 4.7 vs GPT-5.3 Codex

Updated August 29, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

OpenAI logo
Model B
GPT-5.3 Codex

OpenAI

66.16/100

Supported · Public rank #34

90% interval 62.4–70.0

Decision reading

Claude Opus 4.7 has the higher public score estimate, 72.33 versus 66.16, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

2 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 4.7

    Claude Opus 4.7 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 4.7 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

    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

    No shared weighted benchmark basis supports a winner.

    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.

Shared results
2
Claude Opus 4.7 only
6
GPT-5.3 Codex only
6
Like-for-like categories
0 / 8

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.

Agentic

Not comparable
Claude Opus 4.7
Not measured
GPT-5.3 Codex
71.4
Weighted basis
0 vs 2 rows
Reading
Not comparable

Coding

Not comparable
Claude Opus 4.7
Not measured
GPT-5.3 Codex
67.2
Weighted basis
0 vs 3 rows
Reading
Not comparable

Reasoning

Not comparable
Claude Opus 4.7
Not measured
GPT-5.3 Codex
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
Claude Opus 4.7
Not measured
GPT-5.3 Codex
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Math

Not comparable
Claude Opus 4.7
38.6
GPT-5.3 Codex
Not measured
Weighted basis
2 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Claude Opus 4.7
Not measured
GPT-5.3 Codex
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Claude Opus 4.7
Not measured
GPT-5.3 Codex
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Claude Opus 4.7
Not measured
GPT-5.3 Codex
Not measured
Weighted basis
0 vs 0 rows
Reading
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.

A shared-evidence shape is not available.

BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.

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 4.7
$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 4.7
$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 4.7
$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 4.7 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.

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Claude Opus 4.7

Not published

GPT-5.3 Codex

Not published

Reasoning profile

Claude Opus 4.7

Non-Reasoning

GPT-5.3 Codex

Reasoning

Weight access

Claude Opus 4.7

Proprietary

GPT-5.3 Codex

Proprietary

License

Claude Opus 4.7

Proprietary

GPT-5.3 Codex

Proprietary

Release date

Claude Opus 4.7

2026-04-16

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 4.7 has the higher public score estimate, 72.33 versus 66.16, but the 90% score intervals overlap.
Workload cost
Repository review: $0.325 vs $0.1295. Cache-heavy agent loop: $1.35 vs $0.525.
Context tradeoff
Claude Opus 4.7 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 evidence14 rows

Agentic

  • Gert Labs

    Shared source
    Claude Opus 4.765.59%
    GPT-5.3 Codex57.47%

    Claude Opus 4.7 leads this result

  • ResearchClawBench

    Claude Opus 4.720.7%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • OSWorld 2.0

    Claude Opus 4.713.9%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Opus 4.7—
    GPT-5.3 Codex77.3%
    Source

    Not directly comparable

  • OSWorld-Verified

    Claude Opus 4.7—
    GPT-5.3 Codex64.7%
    Source

    Not directly comparable

  • JobBench

    Claude Opus 4.7—
    GPT-5.3 Codex33.7%
    Source

    Not directly comparable

Coding

  • Vibe Code Bench

    Shared source
    Claude Opus 4.771.00%
    GPT-5.3 Codex61.77%

    Claude Opus 4.7 leads this result

  • React Native Evals

    Claude Opus 4.782.8%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • FrontierCode 1.1 Main

    Claude Opus 4.738.5%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • SWE-bench Verified

    Claude Opus 4.7—
    GPT-5.3 Codex85%
    Source

    Not directly comparable

  • SWE-bench Pro

    Claude Opus 4.7—
    GPT-5.3 Codex56.8%
    Source

    Not directly comparable

  • SWE-Rebench

    Claude Opus 4.7—
    GPT-5.3 Codex58.2%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Claude Opus 4.743.793%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Claude Opus 4.722.917%
    Source
    GPT-5.3 Codex—

    Not directly comparable

Frequently asked questions

Which is better, Claude Opus 4.7 or GPT-5.3 Codex?

Claude Opus 4.7 has the higher public score estimate, 72.33 versus 66.16, 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 4.7 or GPT-5.3 Codex?

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 4.7 or GPT-5.3 Codex?

The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.

Which costs less, Claude Opus 4.7 or GPT-5.3 Codex?

For the stated presets, chat costs $0.0175 on Claude Opus 4.7 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 4.7 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 4.7 or GPT-5.3 Codex?

Claude Opus 4.7 has the larger documented context window: 1M, compared with 400K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 29, 2026

Watch Claude Opus 4.7 vs GPT-5.3 Codex

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.