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

56.1/100

Estimated · Public rank #84

90% interval 44.6–67.6

Claude Haiku 4.5 vs DeepSeek V4 Flash 0731

Updated August 13, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B
DeepSeek V4 Flash 0731

DeepSeek

—

Evidence status unavailable

90% interval unavailable

Decision reading

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.

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

    DeepSeek V4 Flash 0731

    DeepSeek V4 Flash 0731 has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    DeepSeek V4 Flash 0731

    DeepSeek V4 Flash 0731 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

    DeepSeek V4 Flash 0731

    DeepSeek V4 Flash 0731 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
1
Claude Haiku 4.5 only
5
DeepSeek V4 Flash 0731 only
32
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
DeepSeek V4 Flash 0731
68.8
Weighted basis
1 vs 2 rows
Reading
Directional only

Agentic

Not comparable
Claude Haiku 4.5
Not measured
DeepSeek V4 Flash 0731
63.8
Weighted basis
0 vs 2 rows
Reading
Not comparable

Reasoning

Not comparable
Claude Haiku 4.5
Not measured
DeepSeek V4 Flash 0731
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
Claude Haiku 4.5
Not measured
DeepSeek V4 Flash 0731
55.3
Weighted basis
0 vs 4 rows
Reading
Not comparable

Math

Not comparable
Claude Haiku 4.5
4.9
DeepSeek V4 Flash 0731
94.8
Weighted basis
2 vs 1 rows
Reading
Not comparable

Multilingual

Not comparable
Claude Haiku 4.5
Not measured
DeepSeek V4 Flash 0731
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Claude Haiku 4.5
Not measured
DeepSeek V4 Flash 0731
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Claude Haiku 4.5
Not measured
DeepSeek V4 Flash 0731
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
DeepSeek V4 Flash 0731
$0.00028
Fits in one request

DeepSeek V4 Flash 0731 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
DeepSeek V4 Flash 0731
$0.00784
Fits in one request

DeepSeek V4 Flash 0731 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
DeepSeek V4 Flash 0731
$0.00616
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

DeepSeek V4 Flash 0731

$0.0028 per 1M cached input tokens

Reasoning profile

Claude Haiku 4.5

Non-Reasoning

DeepSeek V4 Flash 0731

Reasoning

Weight access

Claude Haiku 4.5

Proprietary

DeepSeek V4 Flash 0731

Proprietary

License

Claude Haiku 4.5

Proprietary

DeepSeek V4 Flash 0731

Proprietary

Release date

Claude Haiku 4.5

2025-10-15

DeepSeek V4 Flash 0731

2026-07-31

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
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
Workload cost
Repository review: $0.065 vs $0.00784. Cache-heavy agent loop: $0.09 vs $0.00616.
Context tradeoff
DeepSeek V4 Flash 0731 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 evidence38 rows

Agentic

  • JobBench

    Claude Haiku 4.516.0%
    Source
    DeepSeek V4 Flash 0731—

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073156.9%
    Source

    Not directly comparable

  • BrowseComp

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073173.2%
    Source

    Not directly comparable

  • HLE w/ tools

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073145.1%
    Source

    Not directly comparable

  • MCP Atlas

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073169%
    Source

    Not directly comparable

  • Toolathlon

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073147.8%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073182.7%
    Source

    Not directly comparable

  • CyberGym

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073176.7%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073170.3%
    Source

    Not directly comparable

  • Agents' Last Exam

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073125.2%
    Source

    Not directly comparable

  • AutomationBench

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073125.1%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Claude Haiku 4.573.3%
    Source
    DeepSeek V4 Flash 073179%
    Source

    DeepSeek V4 Flash 0731 leads this result

  • VulcanBench v3

    Claude Haiku 4.578.3%
    Source
    DeepSeek V4 Flash 0731—

    Not directly comparable

  • EEBench

    Claude Haiku 4.53.5%
    Source
    DeepSeek V4 Flash 0731—

    Not directly comparable

  • LiveCodeBench Pass@1-COT

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073191.6%
    Source

    Not directly comparable

  • Codeforces

    Claude Haiku 4.5—
    DeepSeek V4 Flash 07313052.0
    Source

    Not directly comparable

  • SWE-bench Pro

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073152.6%
    Source

    Not directly comparable

  • SWE Multilingual

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073173.3%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073156.9%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073182.7%
    Source

    Not directly comparable

  • NL2Repo

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073154.2%
    Source

    Not directly comparable

  • deepSwe

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073154.4%
    Source

    Not directly comparable

  • DSBench-FullStack

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073168.7%
    Source

    Not directly comparable

  • DSBench-Hard

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073159.6%
    Source

    Not directly comparable

Reasoning

  • MRCR 1M

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073178.7%
    Source

    Not directly comparable

  • CorpusQA 1M

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073160.5%
    Source

    Not directly comparable

Knowledge

  • MMLU-Pro

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073186.2%
    Source

    Not directly comparable

  • SimpleQA

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073134.1%
    Source

    Not directly comparable

  • Chinese-SimpleQA

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073178.9%
    Source

    Not directly comparable

  • GPQA

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073188.1%
    Source

    Not directly comparable

  • GPQA-D

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073188.1%
    Source

    Not directly comparable

  • HLE

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073134.8%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Claude Haiku 4.55.903%
    Source
    DeepSeek V4 Flash 0731—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Claude Haiku 4.52.083%
    Source
    DeepSeek V4 Flash 0731—

    Not directly comparable

  • HMMT Feb 2026

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073194.8%
    Source

    Not directly comparable

  • IMOAnswerBench

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073188.4%
    Source

    Not directly comparable

  • Apex

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073133.0%
    Source

    Not directly comparable

  • Apex Shortlist

    Claude Haiku 4.5—
    DeepSeek V4 Flash 073185.7%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Claude Haiku 4.5 or DeepSeek V4 Flash 0731?

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Claude Haiku 4.5 or DeepSeek V4 Flash 0731?

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 DeepSeek V4 Flash 0731?

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 DeepSeek V4 Flash 0731?

For the stated presets, chat costs $0.0035 on Claude Haiku 4.5 and $0.00028 on DeepSeek V4 Flash 0731; repository review costs $0.065 and $0.00784; the cache-heavy agent loop costs $0.09 and $0.00616. Claude Haiku 4.5 does not fit this workload in one request.

Which has the larger context window, Claude Haiku 4.5 or DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731 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 13, 2026

Watch Claude Haiku 4.5 vs DeepSeek V4 Flash 0731

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

Read a sample issue

Join 2,000+ readers.