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 Opus 4.6

Anthropic

67.98/100

Supported · Public rank #30

90% interval 53.4–82.5

Claude Opus 4.6 vs GPT-5.1

Updated September 3, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

OpenAI logo
Model B
GPT-5.1

OpenAI

53.44/100

Estimated · Public rank #120

90% interval 41.9–65.0

Decision reading

Claude Opus 4.6 has the higher public score estimate, 67.98 versus 53.44, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

4 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 4.6

    Claude Opus 4.6 has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    GPT-5.1

    GPT-5.1 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-5.1

    GPT-5.1 has the lower estimated token cost for this stated workload. Claude Opus 4.6 has no published cached-input rate, so cached tokens use its listed input rate. GPT-5.1 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-5.1

    GPT-5.1 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
4
Claude Opus 4.6 only
29
GPT-5.1 only
0
Like-for-like categories
1 / 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.

Math

Like-for-like
Claude Opus 4.6
36.3
GPT-5.1
26.4
Weighted basis
2 vs 2 rows
Reading
Claude Opus 4.6 leads

Agentic

Not comparable
Claude Opus 4.6
73.0
GPT-5.1
Not measured
Weighted basis
3 vs 0 rows
Reading
Not comparable

Coding

Not comparable
Claude Opus 4.6
68.1
GPT-5.1
Not measured
Weighted basis
3 vs 0 rows
Reading
Not comparable

Reasoning

Not comparable
Claude Opus 4.6
Not measured
GPT-5.1
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
Claude Opus 4.6
69.1
GPT-5.1
Not measured
Weighted basis
4 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Claude Opus 4.6
Not measured
GPT-5.1
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Claude Opus 4.6
77.3
GPT-5.1
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Claude Opus 4.6
Not measured
GPT-5.1
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.

  • FrontierMath v2 (Tier 4)

    Math

    Claude Opus 4.6: 22.900%GPT-5.1: 12.500%Normalized gap 10.4Shared source

  • FrontierMath v2 (Tiers 1-3)

    Math

    Claude Opus 4.6: 40.700%GPT-5.1: 31.034%Normalized gap 9.7Shared 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 4.6
$0.0175
Fits in one request
GPT-5.1
$0.00625
Fits in one request

GPT-5.1 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Opus 4.6
$0.325
Fits in one request
GPT-5.1
$0.0925
Fits in one request

GPT-5.1 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 4.6
$1.35
Fits in one request
Cached input priced at the published list-input rate
GPT-5.1
$0.375
Fits in one request
Cached input priced at the published list-input rate

GPT-5.1 has the lower modeled cost

Claude Opus 4.6 has no published cached-input rate, so cached tokens use its listed input rate. GPT-5.1 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.

Context window

Maximum documented context; output-token limits may be lower.

Claude Opus 4.6

1M

GPT-5.1

400K

API model ID

Claude Opus 4.6

Not sourced

GPT-5.1

Not sourced

Cached-input rate

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

Claude Opus 4.6

Not published

GPT-5.1

Not published

Documented inputs

Claude Opus 4.6

Not sourced

GPT-5.1

Not sourced

Documented outputs

Claude Opus 4.6

Not sourced

GPT-5.1

Not sourced

Provider availability

Claude Opus 4.6

Not sourced

GPT-5.1

Not sourced

Reasoning profile

Claude Opus 4.6

Non-Reasoning

GPT-5.1

Reasoning

Weight access

Claude Opus 4.6

Proprietary

GPT-5.1

Proprietary

License

Claude Opus 4.6

Proprietary

GPT-5.1

Proprietary

Release date

Claude Opus 4.6

2026-02-01

GPT-5.1

2025-11-13

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 4.6 has the higher public score estimate, 67.98 versus 53.44, but the 90% score intervals overlap.
Workload cost
Repository review: $0.325 vs $0.0925. Cache-heavy agent loop: $1.35 vs $0.375.
Context tradeoff
Claude Opus 4.6 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 evidence33 rows

Agentic

  • Terminal-Bench 2.0

    Claude Opus 4.665.4%
    Source
    GPT-5.1—

    Not directly comparable

  • BrowseComp

    Claude Opus 4.683.7%
    Source
    GPT-5.1—

    Not directly comparable

  • OSWorld-Verified

    Claude Opus 4.672.7%
    Source
    GPT-5.1—

    Not directly comparable

  • Claw-Eval

    Claude Opus 4.670.4%
    Source
    GPT-5.1—

    Not directly comparable

  • DeepSearchQA

    Claude Opus 4.673.7%
    Source
    GPT-5.1—

    Not directly comparable

  • CyberGym

    Claude Opus 4.666.6%
    Source
    GPT-5.1—

    Not directly comparable

  • Gert Labs

    Shared source
    Claude Opus 4.661.85%
    GPT-5.141.24%

    Claude Opus 4.6 leads this result

  • ResearchClawBench

    Claude Opus 4.619.9%
    Source
    GPT-5.1—

    Not directly comparable

  • JobBench

    Claude Opus 4.636.7%
    Source
    GPT-5.1—

    Not directly comparable

Coding

  • SWE-bench Verified

    Claude Opus 4.680.8%
    Source
    GPT-5.1—

    Not directly comparable

  • SWE-bench Verified*

    Claude Opus 4.675.6%
    Source
    GPT-5.1—

    Not directly comparable

  • LiveCodeBench Pro

    Claude Opus 4.670.7%
    Source
    GPT-5.1—

    Not directly comparable

  • SWE-bench Pro

    Claude Opus 4.653.4%
    Source
    GPT-5.1—

    Not directly comparable

  • SWE-Rebench

    Claude Opus 4.665.3%
    Source
    GPT-5.1—

    Not directly comparable

  • React Native Evals

    Claude Opus 4.684.1%
    Source
    GPT-5.1—

    Not directly comparable

  • Vibe Code Bench

    Shared source
    Claude Opus 4.657.57%
    GPT-5.124.61%

    Claude Opus 4.6 leads this result

  • FrontierCode 1.1 Main

    Claude Opus 4.626.9%
    Source
    GPT-5.1—

    Not directly comparable

Knowledge

  • GPQA

    Claude Opus 4.691.3%
    Source
    GPT-5.1—

    Not directly comparable

  • GPQA-D

    Claude Opus 4.689.2%
    Source
    GPT-5.1—

    Not directly comparable

  • SuperGPQA

    Claude Opus 4.695%
    Source
    GPT-5.1—

    Not directly comparable

  • MMLU-Pro

    Claude Opus 4.682%
    Source
    GPT-5.1—

    Not directly comparable

  • MMLU-Pro (Arcee)

    Claude Opus 4.689.1%
    Source
    GPT-5.1—

    Not directly comparable

  • HLE

    Claude Opus 4.653%
    Source
    GPT-5.1—

    Not directly comparable

  • HLE w/o tools

    Claude Opus 4.640%
    Source
    GPT-5.1—

    Not directly comparable

  • HealthBench Hard

    Claude Opus 4.614.8%
    Source
    GPT-5.1—

    Not directly comparable

  • MedXpertQA (Text)

    Claude Opus 4.652.1%
    Source
    GPT-5.1—

    Not directly comparable

Math

  • AIME25 (Arcee)

    Claude Opus 4.699.8%
    Source
    GPT-5.1—

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    Claude Opus 4.640.700%
    GPT-5.131.034%

    Claude Opus 4.6 leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    Claude Opus 4.622.900%
    GPT-5.112.500%

    Claude Opus 4.6 leads this result

Multimodal

  • MMMU-Pro

    Claude Opus 4.677.3%
    Source
    GPT-5.1—

    Not directly comparable

  • ERQA

    Claude Opus 4.651.6%
    Source
    GPT-5.1—

    Not directly comparable

  • ScreenSpot Pro

    Claude Opus 4.683.1%
    Source
    GPT-5.1—

    Not directly comparable

  • MedXpertQA (MM)

    Claude Opus 4.664.8%
    Source
    GPT-5.1—

    Not directly comparable

Frequently asked questions

Which is better, Claude Opus 4.6 or GPT-5.1?

Claude Opus 4.6 has the higher public score estimate, 67.98 versus 53.44, 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 4.6 or GPT-5.1?

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 4.6 or GPT-5.1?

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 4.6 or GPT-5.1?

For the stated presets, chat costs $0.0175 on Claude Opus 4.6 and $0.00625 on GPT-5.1; repository review costs $0.325 and $0.0925; the cache-heavy agent loop costs $1.35 and $0.375. Claude Opus 4.6 has no published cached-input rate, so cached tokens use its listed input rate. GPT-5.1 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Claude Opus 4.6 or GPT-5.1?

Claude Opus 4.6 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 3, 2026

Watch Claude Opus 4.6 vs GPT-5.1

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

Read a sample issue

Join 2,000+ readers.