Skip to main content
BenchLM
Advertise

Model comparison

GPT-5.3 Codex vs Grok 4.20

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

GPT-5.3 Codex

OpenAI

65.8/100

Supported · Public rank #30

90% interval 62.3–69.2

Grok 4.20

xAI

53.9/100

Estimated · Public rank #93

90% interval 37.1–70.6

GPT-5.3 Codex has the higher public score estimate, 65.75 versus 53.88, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

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

    Grok 4.20

    Grok 4.20 has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    Grok 4.20

    Grok 4.20 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

    Grok 4.20

    Grok 4.20 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. Grok 4.20 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

    Grok 4.20

    Grok 4.20 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.

Shared results
5
GPT-5.3 Codex only
3
Grok 4.20 only
13
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.

Agentic

Directional only
GPT-5.3 Codex
71.4
Grok 4.20
47.1
Weighted basis
2 vs 1 rows
Reading
Directional only

Coding

Directional only
GPT-5.3 Codex
67.2
Grok 4.20
67.1
Weighted basis
3 vs 2 rows
Reading
Directional only

Reasoning

Not comparable
GPT-5.3 Codex
Not measured
Grok 4.20
53.3
Weighted basis
0 vs 1 rows
Reading
Not comparable

Knowledge

Not comparable
GPT-5.3 Codex
Not measured
Grok 4.20
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Math

Not comparable
GPT-5.3 Codex
Not measured
Grok 4.20
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
GPT-5.3 Codex
Not measured
Grok 4.20
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
GPT-5.3 Codex
Not measured
Grok 4.20
70.1
Weighted basis
0 vs 2 rows
Reading
Not comparable

Instruction following

Not comparable
GPT-5.3 Codex
Not measured
Grok 4.20
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.

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.

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

GPT-5.3 Codex
$0.00875
Fits in one request
Grok 4.20
$0.005
Fits in one request

Grok 4.20 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

GPT-5.3 Codex
$0.1295
Fits in one request
Grok 4.20
$0.118
Fits in one request

Grok 4.20 has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

GPT-5.3 Codex
$0.525
Fits in one request
Cached input priced at the published list-input rate
Grok 4.20
$0.5
Fits in one request
Cached input priced at the published list-input rate

Grok 4.20 has the lower modeled cost

GPT-5.3 Codex has no published cached-input rate, so cached tokens use its listed input rate. Grok 4.20 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.

GPT-5.3 Codex

Not published

Grok 4.20

Not published

Provider availability

GPT-5.3 Codex

Generally Available · OpenAI Responses API

OpenAI model catalog

Grok 4.20

Not sourced

Reasoning profile

GPT-5.3 Codex

Reasoning

Grok 4.20

Reasoning

Weight access

GPT-5.3 Codex

Proprietary

Grok 4.20

Proprietary

License

GPT-5.3 Codex

Proprietary

Grok 4.20

Proprietary

Release date

GPT-5.3 Codex

2026-02-05

Grok 4.20

2026-03-10

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, 65.75 versus 53.88, but the 90% score intervals overlap.
Workload cost
Repository review: $0.1295 vs $0.118. Cache-heavy agent loop: $0.525 vs $0.5.
Context tradeoff
Grok 4.20 has the larger documented window (2M).

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 evidence21 rows

Agentic

  • Terminal-Bench 2.0

    GPT-5.3 Codex77.3%
    Source
    Grok 4.2047.1%
    Source

    GPT-5.3 Codex leads this result

  • OSWorld-Verified

    GPT-5.3 Codex64.7%
    Source
    Grok 4.20—

    Not directly comparable

  • Gert Labs

    Shared source
    GPT-5.3 Codex57.47%
    Grok 4.2038.36%

    GPT-5.3 Codex leads this result

  • JobBench

    GPT-5.3 Codex33.7%
    Source
    Grok 4.20—

    Not directly comparable

  • DeepSearchQA

    GPT-5.3 Codex—
    Grok 4.2062.8%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    GPT-5.3 Codex85%
    Source
    Grok 4.2076.7%
    Source

    GPT-5.3 Codex leads this result

  • SWE-bench Pro

    GPT-5.3 Codex56.8%
    Source
    Grok 4.2051.8%
    Source

    GPT-5.3 Codex leads this result

  • SWE-Rebench

    GPT-5.3 Codex58.2%
    Source
    Grok 4.20—

    Not directly comparable

  • Vibe Code Bench

    Shared source
    GPT-5.3 Codex61.77%
    Grok 4.204.06%

    GPT-5.3 Codex leads this result

  • LiveCodeBench Pro

    GPT-5.3 Codex—
    Grok 4.2074.2%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-2

    GPT-5.3 Codex—
    Grok 4.2053.3%
    Source

    Not directly comparable

  • ARC-AGI-3

    GPT-5.3 Codex—
    Grok 4.200.1%
    Source

    Not directly comparable

Knowledge

  • GPQA-D

    GPT-5.3 Codex—
    Grok 4.2088.5%
    Source

    Not directly comparable

  • HLE w/o tools

    GPT-5.3 Codex—
    Grok 4.2031.6%
    Source

    Not directly comparable

  • HealthBench Hard

    GPT-5.3 Codex—
    Grok 4.2020.3%
    Source

    Not directly comparable

  • MedXpertQA (Text)

    GPT-5.3 Codex—
    Grok 4.2050.2%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    GPT-5.3 Codex—
    Grok 4.2075.2%
    Source

    Not directly comparable

  • CharXiv

    GPT-5.3 Codex—
    Grok 4.2060.9%
    Source

    Not directly comparable

  • ERQA

    GPT-5.3 Codex—
    Grok 4.2054.1%
    Source

    Not directly comparable

  • SimpleVQA

    GPT-5.3 Codex—
    Grok 4.2057.4%
    Source

    Not directly comparable

  • MedXpertQA (MM)

    GPT-5.3 Codex—
    Grok 4.2065.8%
    Source

    Not directly comparable

Frequently asked questions

Which is better, GPT-5.3 Codex or Grok 4.20?

GPT-5.3 Codex has the higher public score estimate, 65.75 versus 53.88, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, GPT-5.3 Codex or Grok 4.20?

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, GPT-5.3 Codex or Grok 4.20?

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, GPT-5.3 Codex or Grok 4.20?

For the stated presets, chat costs $0.00875 on GPT-5.3 Codex and $0.005 on Grok 4.20; repository review costs $0.1295 and $0.118; the cache-heavy agent loop costs $0.525 and $0.5. GPT-5.3 Codex has no published cached-input rate, so cached tokens use its listed input rate. Grok 4.20 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, GPT-5.3 Codex or Grok 4.20?

Grok 4.20 has the larger documented context window: 2M, compared with 400K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated July 29, 2026

Watch GPT-5.3 Codex vs Grok 4.20

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

Read a sample issue

Join 2,000+ readers.