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 free brief
BenchLM
Model A
Claude Haiku 4.5

Anthropic

57.1/100

Estimated · Public rank #86

90% interval 45.5–68.6

Claude Haiku 4.5 vs Claude Sonnet 5

Updated August 15, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B
Claude Sonnet 5

Anthropic

64.8/100

Estimated · Public rank #37

90% interval 50.5–79.1

Decision reading

Claude Sonnet 5 has the higher public score estimate, 64.78 versus 57.06, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

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

    Claude Sonnet 5

    Claude Sonnet 5 has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    Claude Haiku 4.5

    Claude Haiku 4.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

Show secondary and unsupported calls

  • Repository review cost

    50K fresh input + 3K output tokens

    Claude Haiku 4.5

    Claude Haiku 4.5 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

  • Cache-heavy agent loop cost

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

    Not enough matched evidence

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Claude Haiku 4.5 does not fit this workload in one request.

    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
2
Claude Haiku 4.5 only
4
Claude Sonnet 5 only
17
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 Haiku 4.5
73.3
Claude Sonnet 5
76.7
Weighted basis
1 vs 2 rows
Reading
Directional only

Agentic

Not comparable
Claude Haiku 4.5
Not measured
Claude Sonnet 5
81.9
Weighted basis
0 vs 3 rows
Reading
Not comparable

Reasoning

Not comparable
Claude Haiku 4.5
Not measured
Claude Sonnet 5
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
Claude Haiku 4.5
Not measured
Claude Sonnet 5
57.4
Weighted basis
0 vs 1 rows
Reading
Not comparable

Math

Not comparable
Claude Haiku 4.5
4.9
Claude Sonnet 5
Not measured
Weighted basis
2 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Claude Haiku 4.5
Not measured
Claude Sonnet 5
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Claude Haiku 4.5
Not measured
Claude Sonnet 5
88.3
Weighted basis
0 vs 1 rows
Reading
Not comparable

Instruction following

Not comparable
Claude Haiku 4.5
Not measured
Claude Sonnet 5
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 Haiku 4.5
$0.0035
Fits in one request
Claude Sonnet 5
$0.007
Fits in one request

Claude Haiku 4.5 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Haiku 4.5
$0.065
Fits in one request
Claude Sonnet 5
$0.13
Fits in one request

Claude Haiku 4.5 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 Haiku 4.5
$0.09
Does not fit in one request
Claude Sonnet 5
$0.18
Fits in one request

Claude Haiku 4.5 does not fit this workload in one request.

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 Haiku 4.5

$0.1 per 1M cached input tokens

Claude API pricing

Claude Sonnet 5

$0.2 per 1M cached input tokens

Claude API pricing

Provider availability

Claude Haiku 4.5

Not sourced

Claude Sonnet 5

Generally Available · Claude API

Anthropic model overview

Reasoning profile

Claude Haiku 4.5

Non-Reasoning

Claude Sonnet 5

Reasoning

Weight access

Claude Haiku 4.5

Proprietary

Claude Sonnet 5

Proprietary

License

Claude Haiku 4.5

Proprietary

Claude Sonnet 5

Proprietary

Release date

Claude Haiku 4.5

2025-10-15

Claude Sonnet 5

2026-06-30

If you already use one of these models
Deployment change
Both entries list Anthropic as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
Quality signal
Claude Sonnet 5 has the higher public score estimate, 64.78 versus 57.06, but the 90% score intervals overlap.
Workload cost
Repository review: $0.065 vs $0.13. Cache-heavy agent loop: $0.09 vs $0.18.
Context tradeoff
Claude Sonnet 5 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 evidence23 rows

Agentic

  • JobBench

    Claude Haiku 4.516.0%
    Source
    Claude Sonnet 5—

    Not directly comparable

  • Terminal-Bench 3.0

    Claude Haiku 4.5—
    Claude Sonnet 514.6%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Haiku 4.5—
    Claude Sonnet 580.4%
    Source

    Not directly comparable

  • BrowseComp

    Claude Haiku 4.5—
    Claude Sonnet 584.7%
    Source

    Not directly comparable

  • HLE w/ tools

    Claude Haiku 4.5—
    Claude Sonnet 557.4%
    Source

    Not directly comparable

  • OSWorld-Verified

    Claude Haiku 4.5—
    Claude Sonnet 581.2%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Claude Haiku 4.573.3%
    Source
    Claude Sonnet 585.2%
    Source

    Claude Sonnet 5 leads this result

  • VulcanBench v3

    Claude Haiku 4.578.3%
    Source
    Claude Sonnet 5—

    Not directly comparable

  • EEBench

    Shared source
    Claude Haiku 4.53.5%
    Claude Sonnet 540.3%

    Claude Sonnet 5 leads this result

  • SWE-bench Pro

    Claude Haiku 4.5—
    Claude Sonnet 563.2%
    Source

    Not directly comparable

  • SWE Multilingual

    Claude Haiku 4.5—
    Claude Sonnet 578.3%
    Source

    Not directly comparable

  • SWE Multimodal

    Claude Haiku 4.5—
    Claude Sonnet 528.1%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Haiku 4.5—
    Claude Sonnet 580.4%
    Source

    Not directly comparable

  • FrontierCode 1.1 Main

    Claude Haiku 4.5—
    Claude Sonnet 542.7%
    Source

    Not directly comparable

  • cursorBench32

    Claude Haiku 4.5—
    Claude Sonnet 561.5%
    Source

    Not directly comparable

  • APEX-SWE

    Claude Haiku 4.5—
    Claude Sonnet 546.4%
    Source

    Not directly comparable

  • 3DCodeBench

    Claude Haiku 4.5—
    Claude Sonnet 539.2%
    Source

    Not directly comparable

Knowledge

  • HLE

    Claude Haiku 4.5—
    Claude Sonnet 557.4%
    Source

    Not directly comparable

  • HLE w/o tools

    Claude Haiku 4.5—
    Claude Sonnet 543.2%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Claude Haiku 4.55.903%
    Source
    Claude Sonnet 5—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Claude Haiku 4.52.083%
    Source
    Claude Sonnet 5—

    Not directly comparable

Multimodal

  • CharXiv

    Claude Haiku 4.5—
    Claude Sonnet 588.3%
    Source

    Not directly comparable

  • CharXiv w/o tools

    Claude Haiku 4.5—
    Claude Sonnet 577%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Claude Haiku 4.5 or Claude Sonnet 5?

Claude Sonnet 5 has the higher public score estimate, 64.78 versus 57.06, 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 Haiku 4.5 or Claude Sonnet 5?

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 Haiku 4.5 or Claude Sonnet 5?

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 Haiku 4.5 or Claude Sonnet 5?

For the stated presets, chat costs $0.0035 on Claude Haiku 4.5 and $0.007 on Claude Sonnet 5; repository review costs $0.065 and $0.13; the cache-heavy agent loop costs $0.09 and $0.18. Claude Haiku 4.5 does not fit this workload in one request.

Which has the larger context window, Claude Haiku 4.5 or Claude Sonnet 5?

Claude Sonnet 5 has the larger documented context window: 1M, compared with 200K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 15, 2026

Watch Claude Haiku 4.5 vs Claude Sonnet 5

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

Read a sample issue

Join 2,000+ readers.