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 (Adaptive)

Anthropic

72.41/100

Estimated · Public rank #15

90% interval 62.5–82.3

Claude Opus 4.7 (Adaptive) vs Claude Opus 4.8

Updated August 26, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Anthropic logo
Model B
Claude Opus 4.8

Anthropic

76.45/100

Supported · Public rank #8

90% interval 73.8–79.1

Decision reading

Claude Opus 4.8 has the higher public score estimate, 76.45 versus 72.41, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

17 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.

  • Coding work

    Code generation, repair, and software-engineering tasks

    Claude Opus 4.8

    Claude Opus 4.8 leads on the same 2 weighted benchmark rows.

    Confidence: limited

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Claude Opus 4.8

    Claude Opus 4.8 leads on the same 3 weighted benchmark rows.

    Confidence: stronger

Show secondary and unsupported calls

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    No clear pick

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

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

    No clear pick

    A complete comparable API-rate estimate is not available for both models.

    Confidence: rate-fallback

  • Repository review cost

    50K fresh input + 3K output tokens

    No clear pick

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

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
17
Claude Opus 4.7 (Adaptive) only
4
Claude Opus 4.8 only
16
Like-for-like categories
5 / 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

Like-for-like
Claude Opus 4.7 (Adaptive)
75.1
Claude Opus 4.8
80.3
Weighted basis
3 vs 3 rows
Reading
Claude Opus 4.8 leads

Coding

Like-for-like
Claude Opus 4.7 (Adaptive)
78.6
Claude Opus 4.8
81.1
Weighted basis
2 vs 2 rows
Reading
Claude Opus 4.8 leads

Reasoning

Like-for-like
Claude Opus 4.7 (Adaptive)
75.8
Claude Opus 4.8
72.1
Weighted basis
1 vs 1 rows
Reading
Claude Opus 4.7 (Adaptive) leads

Knowledge

Like-for-like
Claude Opus 4.7 (Adaptive)
60.0
Claude Opus 4.8
62.7
Weighted basis
2 vs 2 rows
Reading
Claude Opus 4.8 leads

Multimodal

Like-for-like
Claude Opus 4.7 (Adaptive)
65.1
Claude Opus 4.8
77.0
Weighted basis
2 vs 2 rows
Reading
Claude Opus 4.8 leads

Math

Not comparable
Claude Opus 4.7 (Adaptive)
Not measured
Claude Opus 4.8
53.9
Weighted basis
0 vs 3 rows
Reading
Not comparable

Multilingual

Not comparable
Claude Opus 4.7 (Adaptive)
Not measured
Claude Opus 4.8
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Claude Opus 4.7 (Adaptive)
Not measured
Claude Opus 4.8
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 Opus 4.7 (Adaptive)
$0.0175
Fits in one request
Claude Opus 4.8
$0.0175
Fits in one request

Modeled costs are equal

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Opus 4.7 (Adaptive)
$0.325
Fits in one request
Claude Opus 4.8
$0.325
Fits in one request

Modeled costs are equal

Costs use the listed standard API rates.

Cache-heavy agent loop

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

Claude Opus 4.7 (Adaptive)
$1.35
Fits in one request
Cached input priced at the published list-input rate
Claude Opus 4.8
$1.35
Fits in one request
Cached input priced at the published list-input rate

Modeled costs are equal

Claude Opus 4.7 (Adaptive) has no published cached-input rate, so cached tokens use its listed input rate. Claude Opus 4.8 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 4.7 (Adaptive)

1M

Claude Opus 4.8

1M

Anthropic model overview

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 (Adaptive)

Not published

Claude Opus 4.8

Not published

Provider availability

Claude Opus 4.7 (Adaptive)

Not sourced

Claude Opus 4.8

Generally Available · Claude API

Anthropic model overview

Reasoning profile

Claude Opus 4.7 (Adaptive)

Reasoning

Claude Opus 4.8

Reasoning

Weight access

Claude Opus 4.7 (Adaptive)

Proprietary

Claude Opus 4.8

Proprietary

License

Claude Opus 4.7 (Adaptive)

Proprietary

Claude Opus 4.8

Proprietary

Release date

Claude Opus 4.7 (Adaptive)

2026-04-16

Claude Opus 4.8

2026-05-28

If you are considering the documented upgrade path
Deployment change
Both entries list Anthropic as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
Quality signal
Claude Opus 4.8 has the higher public score estimate, 76.45 versus 72.41, but the 90% score intervals overlap.
Workload cost
Repository review: $0.325 vs $0.325. Cache-heavy agent loop: $1.35 vs $1.35.
Context tradeoff
Both models list 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 evidence37 rows

Agentic

  • Terminal-Bench 2.0

    Claude Opus 4.7 (Adaptive)69.4%
    Source
    Claude Opus 4.874.6%
    Source

    Claude Opus 4.8 leads this result

  • BrowseComp

    Claude Opus 4.7 (Adaptive)79.3%
    Source
    Claude Opus 4.884.3%
    Source

    Claude Opus 4.8 leads this result

  • MCP Atlas

    Claude Opus 4.7 (Adaptive)77.3%
    Source
    Claude Opus 4.882.2%
    Source

    Claude Opus 4.8 leads this result

  • OSWorld-Verified

    Claude Opus 4.7 (Adaptive)78%
    Source
    Claude Opus 4.883.4%
    Source

    Claude Opus 4.8 leads this result

  • CyberGym

    Claude Opus 4.7 (Adaptive)73.1%
    Source
    Claude Opus 4.8—

    Not directly comparable

  • OSWorld 2.0

    Shared source
    Claude Opus 4.7 (Adaptive)18.2%
    Claude Opus 4.820.6%

    Claude Opus 4.8 leads this result

  • JobBench

    Claude Opus 4.7 (Adaptive)45.9%
    Source
    Claude Opus 4.8—

    Not directly comparable

  • Terminal-Bench 3.0

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.821.1%
    Source

    Not directly comparable

  • DeepSearchQA

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.893.1%
    Source

    Not directly comparable

  • Finance Agent v2

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.853.9%
    Source

    Not directly comparable

  • Toolathlon

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.859.9%
    Source

    Not directly comparable

  • Gert Labs

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.872.97%
    Source

    Not directly comparable

  • ResearchClawBench

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.821.1%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Claude Opus 4.7 (Adaptive)87.6%
    Source
    Claude Opus 4.888.6%
    Source

    Claude Opus 4.8 leads this result

  • SWE-bench Pro

    Claude Opus 4.7 (Adaptive)64.3%
    Source
    Claude Opus 4.869.2%
    Source

    Claude Opus 4.8 leads this result

  • Terminal-Bench 2.0

    Claude Opus 4.7 (Adaptive)69.4%
    Source
    Claude Opus 4.874.6%
    Source

    Claude Opus 4.8 leads this result

  • SWE Multilingual

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.884.4%
    Source

    Not directly comparable

  • SWE Multimodal

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.838.4%
    Source

    Not directly comparable

  • cursorBench31

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.858.4%
    Source

    Not directly comparable

  • cursorBench32

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.862.3%
    Source

    Not directly comparable

  • FrontierCode 1.1 Main

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.846.5%
    Source

    Not directly comparable

Reasoning

  • MRCR v2 128K-256K

    Claude Opus 4.7 (Adaptive)59.2%
    Source
    Claude Opus 4.8—

    Not directly comparable

  • ARC-AGI-2

    Claude Opus 4.7 (Adaptive)75.8%
    Source
    Claude Opus 4.872.1%
    Source

    Claude Opus 4.7 (Adaptive) leads this result

  • ARC-AGI-3

    Shared source
    Claude Opus 4.7 (Adaptive)0.2%
    Claude Opus 4.81.5%

    Claude Opus 4.8 leads this result

Knowledge

  • GPQA

    Claude Opus 4.7 (Adaptive)94.2%
    Source
    Claude Opus 4.893.6%
    Source

    Claude Opus 4.7 (Adaptive) leads this result

  • GPQA-D

    Claude Opus 4.7 (Adaptive)94.2%
    Source
    Claude Opus 4.893.6%
    Source

    Claude Opus 4.7 (Adaptive) leads this result

  • HLE

    Claude Opus 4.7 (Adaptive)54.7%
    Source
    Claude Opus 4.857.9%
    Source

    Claude Opus 4.8 leads this result

  • HLE w/o tools

    Claude Opus 4.7 (Adaptive)46.9%
    Source
    Claude Opus 4.849.8%
    Source

    Claude Opus 4.8 leads this result

Math

  • FrontierMath (legacy)

    Claude Opus 4.7 (Adaptive)43.8%
    Source
    Claude Opus 4.8—

    Not directly comparable

  • USAMO 2026

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.896.7%
    Source

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.847.241%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.831.250%
    Source

    Not directly comparable

Multilingual

  • INCLUDE

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.887.6%
    Source

    Not directly comparable

Multimodal

  • OfficeQA Pro

    Claude Opus 4.7 (Adaptive)43.6%
    Source
    Claude Opus 4.866.2%
    Source

    Claude Opus 4.8 leads this result

  • CharXiv

    Claude Opus 4.7 (Adaptive)91%
    Source
    Claude Opus 4.889.9%
    Source

    Claude Opus 4.7 (Adaptive) leads this result

  • CharXiv w/o tools

    Claude Opus 4.7 (Adaptive)82.1%
    Source
    Claude Opus 4.880.5%
    Source

    Claude Opus 4.7 (Adaptive) leads this result

  • ScreenSpot Pro

    Claude Opus 4.7 (Adaptive)—
    Claude Opus 4.887.9%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Claude Opus 4.7 (Adaptive) or Claude Opus 4.8?

Claude Opus 4.8 has the higher public score estimate, 76.45 versus 72.41, 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 (Adaptive) or Claude Opus 4.8?

Claude Opus 4.8 leads the like-for-like coding comparison across 2 shared weighted benchmark rows.

Which is better for agentic tasks, Claude Opus 4.7 (Adaptive) or Claude Opus 4.8?

Claude Opus 4.8 leads the like-for-like agentic tasks comparison across 3 shared weighted benchmark rows.

Which costs less, Claude Opus 4.7 (Adaptive) or Claude Opus 4.8?

For the stated presets, chat costs $0.0175 on Claude Opus 4.7 (Adaptive) and $0.0175 on Claude Opus 4.8; repository review costs $0.325 and $0.325; the cache-heavy agent loop costs $1.35 and $1.35. Claude Opus 4.7 (Adaptive) has no published cached-input rate, so cached tokens use its listed input rate. Claude Opus 4.8 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Claude Opus 4.7 (Adaptive) or Claude Opus 4.8?

Both models list the same context window, 1M.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 26, 2026

Watch Claude Opus 4.7 (Adaptive) vs Claude Opus 4.8

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

Read a sample issue

Join 2,000+ readers.