Skip to main content
Radar

Provider changes are easy to miss. Radar watches releases, pricing, deprecations, and incidents at the source.Provider changes are easy to miss.

See Radar
BenchLM
Advertise

Model comparison

GPT-5.3 Codex vs GPT-5.6 Sol

Updated August 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

GPT-5.3 Codex

OpenAI

65.7/100

Supported · Public rank #30

90% interval 62.4–69.1

GPT-5.6 Sol

OpenAI

81.5/100

Supported · Public rank #4

90% interval 77.7–85.3

GPT-5.6 Sol has the higher public score, 81.48 versus 65.74, and the 90% score intervals do not overlap.

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

    GPT-5.6 Sol

    GPT-5.6 Sol 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-5.6 Sol

    GPT-5.6 Sol 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.

Shared results
2
GPT-5.3 Codex only
6
GPT-5.6 Sol only
22
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
GPT-5.6 Sol
92.0
Weighted basis
2 vs 2 rows
Reading
Directional only

Coding

Directional only
GPT-5.3 Codex
67.2
GPT-5.6 Sol
64.6
Weighted basis
3 vs 1 rows
Reading
Directional only

Reasoning

Not comparable
GPT-5.3 Codex
Not measured
GPT-5.6 Sol
92.5
Weighted basis
0 vs 1 rows
Reading
Not comparable

Knowledge

Not comparable
GPT-5.3 Codex
Not measured
GPT-5.6 Sol
94.6
Weighted basis
0 vs 1 rows
Reading
Not comparable

Math

Not comparable
GPT-5.3 Codex
Not measured
GPT-5.6 Sol
87.5
Weighted basis
0 vs 2 rows
Reading
Not comparable

Multilingual

Not comparable
GPT-5.3 Codex
Not measured
GPT-5.6 Sol
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
GPT-5.3 Codex
Not measured
GPT-5.6 Sol
83.0
Weighted basis
0 vs 1 rows
Reading
Not comparable

Instruction following

Not comparable
GPT-5.3 Codex
Not measured
GPT-5.6 Sol
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
GPT-5.6 Sol
$0.02
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

GPT-5.3 Codex
$0.1295
Fits in one request
GPT-5.6 Sol
$0.34
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

GPT-5.3 Codex
$0.525
Fits in one request
Cached input priced at the published list-input rate
GPT-5.6 Sol
$0.5
Fits in one request

GPT-5.6 Sol 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.

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

GPT-5.6 Sol

$0.5 per 1M cached input tokens

OpenAI pricing

Reasoning profile

GPT-5.3 Codex

Reasoning

GPT-5.6 Sol

Reasoning

Weight access

GPT-5.3 Codex

Proprietary

GPT-5.6 Sol

Proprietary

License

GPT-5.3 Codex

Proprietary

GPT-5.6 Sol

Proprietary

Release date

GPT-5.3 Codex

2026-02-05

GPT-5.6 Sol

2026-07-09

If you already use one of these models
Deployment change
Both entries list OpenAI as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
Quality signal
GPT-5.6 Sol has the higher public score, 81.48 versus 65.74, and the 90% score intervals do not overlap.
Workload cost
Repository review: $0.1295 vs $0.34. Cache-heavy agent loop: $0.525 vs $0.5.
Context tradeoff
GPT-5.6 Sol 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 evidence30 rows

Agentic

  • Terminal-Bench 2.0

    GPT-5.3 Codex77.3%
    Source
    GPT-5.6 Sol91.9%
    Source

    GPT-5.6 Sol leads this result

  • OSWorld-Verified

    GPT-5.3 Codex64.7%
    Source
    GPT-5.6 Sol—

    Not directly comparable

  • Gert Labs

    GPT-5.3 Codex57.47%
    Source
    GPT-5.6 Sol—

    Not directly comparable

  • JobBench

    GPT-5.3 Codex33.7%
    Source
    GPT-5.6 Sol—

    Not directly comparable

  • BrowseComp

    GPT-5.3 Codex—
    GPT-5.6 Sol92.2%
    Source

    Not directly comparable

  • OSWorld 2.0

    GPT-5.3 Codex—
    GPT-5.6 Sol62.6%
    Source

    Not directly comparable

  • CyberGym

    GPT-5.3 Codex—
    GPT-5.6 Sol84.5%
    Source

    Not directly comparable

  • ExploitGym

    GPT-5.3 Codex—
    GPT-5.6 Sol33.7%
    Source

    Not directly comparable

  • Toolathlon

    GPT-5.3 Codex—
    GPT-5.6 Sol58%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    GPT-5.3 Codex85%
    Source
    GPT-5.6 Sol—

    Not directly comparable

  • SWE-bench Pro

    GPT-5.3 Codex56.8%
    Source
    GPT-5.6 Sol64.6%
    Source

    GPT-5.6 Sol leads this result

  • SWE-Rebench

    GPT-5.3 Codex58.2%
    Source
    GPT-5.6 Sol—

    Not directly comparable

  • Vibe Code Bench

    GPT-5.3 Codex61.77%
    Source
    GPT-5.6 Sol—

    Not directly comparable

  • Terminal-Bench 2.0

    GPT-5.3 Codex—
    GPT-5.6 Sol91.9%
    Source

    Not directly comparable

  • deepSwe

    GPT-5.3 Codex—
    GPT-5.6 Sol72.7%
    Source

    Not directly comparable

  • FrontierCode 1.1 Extended

    GPT-5.3 Codex—
    GPT-5.6 Sol60.6%
    Source

    Not directly comparable

  • cursorBench32

    GPT-5.3 Codex—
    GPT-5.6 Sol67.2%
    Source

    Not directly comparable

  • VulcanBench v3

    GPT-5.3 Codex—
    GPT-5.6 Sol87.0%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-2

    GPT-5.3 Codex—
    GPT-5.6 Sol92.5%
    Source

    Not directly comparable

  • ARC-AGI-3

    GPT-5.3 Codex—
    GPT-5.6 Sol7.8%
    Source

    Not directly comparable

  • GeneBench-Pro

    GPT-5.3 Codex—
    GPT-5.6 Sol28.7%
    Source

    Not directly comparable

Knowledge

  • GPQA

    GPT-5.3 Codex—
    GPT-5.6 Sol94.6%
    Source

    Not directly comparable

  • GPQA-D

    GPT-5.3 Codex—
    GPT-5.6 Sol94.6%
    Source

    Not directly comparable

  • HealthBench Professional

    GPT-5.3 Codex—
    GPT-5.6 Sol60.5%
    Source

    Not directly comparable

  • HealthBench Hard

    GPT-5.3 Codex—
    GPT-5.6 Sol33.1%
    Source

    Not directly comparable

Math

  • FrontierMath (legacy)

    GPT-5.3 Codex—
    GPT-5.6 Sol89%
    Source

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    GPT-5.3 Codex—
    GPT-5.6 Sol89.000%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    GPT-5.3 Codex—
    GPT-5.6 Sol83.000%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    GPT-5.3 Codex—
    GPT-5.6 Sol83%
    Source

    Not directly comparable

  • MMMU-Pro w/ Python

    GPT-5.3 Codex—
    GPT-5.6 Sol84.6%
    Source

    Not directly comparable

Frequently asked questions

Which is better, GPT-5.3 Codex or GPT-5.6 Sol?

GPT-5.6 Sol has the higher public score, 81.48 versus 65.74, 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, GPT-5.3 Codex or GPT-5.6 Sol?

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 GPT-5.6 Sol?

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 GPT-5.6 Sol?

For the stated presets, chat costs $0.00875 on GPT-5.3 Codex and $0.02 on GPT-5.6 Sol; repository review costs $0.1295 and $0.34; 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.

Which has the larger context window, GPT-5.3 Codex or GPT-5.6 Sol?

GPT-5.6 Sol has the larger documented context window: 1.05M, compared with 400K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 10, 2026

Watch GPT-5.3 Codex vs GPT-5.6 Sol

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

Read a sample issue

Join 2,000+ readers.