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.

See the free Radar Brief
BenchLM
Anthropic logo
Model A
Claude Fable 5.1

Anthropic

82.74/100

Estimated · Public rank #1

90% interval 71.2–94.3

Claude Fable 5.1 vs GPT-5.3 Codex

Updated September 1, 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

65.6/100

Supported · Public rank #35

90% interval 61.5–69.7

Decision reading

Claude Fable 5.1 has the higher public score, 82.74 versus 65.6, and the 90% score intervals do not overlap.

1 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 Fable 5.1

    Claude Fable 5.1 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. 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

    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
1
Claude Fable 5.1 only
17
GPT-5.3 Codex only
7
Like-for-like categories
0 / 8

1 category uses 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 Fable 5.1
81.2
GPT-5.3 Codex
67.2
Weighted basis
1 vs 3 rows
Reading
Directional only

Agentic

Not comparable
Claude Fable 5.1
Not measured
GPT-5.3 Codex
71.4
Weighted basis
0 vs 2 rows
Reading
Not comparable

Reasoning

Not comparable
Claude Fable 5.1
90.0
GPT-5.3 Codex
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
Claude Fable 5.1
65.0
GPT-5.3 Codex
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Math

Not comparable
Claude Fable 5.1
Not measured
GPT-5.3 Codex
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Claude Fable 5.1
Not measured
GPT-5.3 Codex
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Claude Fable 5.1
Not measured
GPT-5.3 Codex
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Claude Fable 5.1
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.

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

Claude Fable 5.1
$0.035
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 Fable 5.1
$0.65
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 Fable 5.1
$0.75
Fits in one request
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

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 Fable 5.1

$0.25 per 1M cached input tokens

Anthropic Fable 5.1 launch

GPT-5.3 Codex

Not published

Reasoning profile

Claude Fable 5.1

Reasoning

GPT-5.3 Codex

Reasoning

Weight access

Claude Fable 5.1

Proprietary

GPT-5.3 Codex

Proprietary

License

Claude Fable 5.1

Proprietary

GPT-5.3 Codex

Proprietary

Release date

Claude Fable 5.1

2026-09-01

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 Fable 5.1 has the higher public score, 82.74 versus 65.6, and the 90% score intervals do not overlap.
Workload cost
Repository review: $0.65 vs $0.1295. Cache-heavy agent loop: $0.75 vs $0.525.
Context tradeoff
Claude Fable 5.1 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 evidence25 rows

Agentic

  • Terminal-Bench 4.0

    Claude Fable 5.155.80%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • Terminal-Bench-Science 0.1

    Claude Fable 5.152.6%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • OSWorld 2.0

    Claude Fable 5.141.7%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • AutomationBench

    Claude Fable 5.131.4%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • Toolathlon-Verified

    Claude Fable 5.177.8%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • Toolathlon Verified Pass@3

    Claude Fable 5.181.5%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • Toolathlon Verified Pass³

    Claude Fable 5.173.1%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • Toolathlon Verified avg. turns

    Claude Fable 5.123.7 turns
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Fable 5.1—
    GPT-5.3 Codex77.3%
    Source

    Not directly comparable

  • OSWorld-Verified

    Claude Fable 5.1—
    GPT-5.3 Codex64.7%
    Source

    Not directly comparable

  • Gert Labs

    Claude Fable 5.1—
    GPT-5.3 Codex57.47%
    Source

    Not directly comparable

  • JobBench

    Claude Fable 5.1—
    GPT-5.3 Codex33.7%
    Source

    Not directly comparable

Coding

  • SWE-bench Pro

    Claude Fable 5.181.2%
    Source
    GPT-5.3 Codex56.8%
    Source

    Claude Fable 5.1 leads this result

  • SWE Multilingual

    Claude Fable 5.189.1%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • SWE Multimodal

    Claude Fable 5.154.7%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • deepSwe

    Claude Fable 5.167.4%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • ProgramBench

    Claude Fable 5.187.6%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • cursorBench32

    Claude Fable 5.173.4%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • SWE-bench Verified

    Claude Fable 5.1—
    GPT-5.3 Codex85%
    Source

    Not directly comparable

  • SWE-Rebench

    Claude Fable 5.1—
    GPT-5.3 Codex58.2%
    Source

    Not directly comparable

  • Vibe Code Bench

    Claude Fable 5.1—
    GPT-5.3 Codex61.77%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-1

    Claude Fable 5.197.50%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • ARC-AGI-2

    Claude Fable 5.190%
    Source
    GPT-5.3 Codex—

    Not directly comparable

Knowledge

  • HLE

    Claude Fable 5.165%
    Source
    GPT-5.3 Codex—

    Not directly comparable

  • HLE w/o tools

    Claude Fable 5.160.9%
    Source
    GPT-5.3 Codex—

    Not directly comparable

Frequently asked questions

Which is better, Claude Fable 5.1 or GPT-5.3 Codex?

Claude Fable 5.1 has the higher public score, 82.74 versus 65.6, 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 Fable 5.1 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 Fable 5.1 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 Fable 5.1 or GPT-5.3 Codex?

For the stated presets, chat costs $0.035 on Claude Fable 5.1 and $0.00875 on GPT-5.3 Codex; repository review costs $0.65 and $0.1295; the cache-heavy agent loop costs $0.75 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 Fable 5.1 or GPT-5.3 Codex?

Claude Fable 5.1 has the larger documented context window: 1M, compared with 400K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 1, 2026

Watch Claude Fable 5.1 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.