Skip to main content
BenchLM
Data

Claude Haiku 5.5 vs Qwen3.7 Plus

Updated November 21, 2026. Rank says Claude Haiku 5.5 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Claude Haiku 5.5 has the higher public point estimate, 63.5 versus 53.7. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. 2 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Anthropic logo

Anthropic

63.5/100

Supported · Public rank #38

90% interval 59.5–67.6

Model B
Alibaba logo

Alibaba

53.7/100

Supported · Public rank #81

Conditional range 49.0–58.3

API price per 1M tokens

Claude Haiku 5.5: $0.10 input / $0.50 output

Qwen3.7 Plus: No comparable API price

Context window

Claude Haiku 5.5: 1M

Qwen3.7 Plus: 1M

Released

Claude Haiku 5.5: October 7, 2026

Qwen3.7 Plus: June 3, 2026

Shared results
2
Claude Haiku 5.5 only
25
Qwen3.7 Plus only
52
Like-for-like categories
2 / 8
Supported: Claude Haiku 5.5 and Qwen3.7 Plus. Conditional ranges do not establish rank confidence.How the comparison works

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.

  • Agentic work

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

    Claude Haiku 5.5

    Claude Haiku 5.5 has the higher public agentic point estimate, 68.3 to 53.8, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited
Show secondary and unsupported calls
  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Qwen3.7 Plus is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.

    Confidence: limited
  • 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

    Not enough matched evidence

    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

    Not enough matched evidence

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

    Confidence: listed-rates
  • Repository review cost

    50K fresh input + 3K output tokens

    Not enough matched evidence

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

    Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

67.9Claude Haiku 5.552.4Qwen3.7 Plus

Directional only · BenchAlign v6.0

Claude Haiku 5.5 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

6 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

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 (Tiers 1-3)Math

    Normalized gap 40.7
    Claude Haiku 5.5:75.088%
    Qwen3.7 Plus:34.386%
Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v6.0 lane in every category, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Like-for-like
Claude Haiku 5.5
68.3
Supported · #25/182
Qwen3.7 Plus
53.8
Supported · #81/182
Basis
BenchAlign v6.0 lane · 9 vs 12 public rows
Reading
Claude Haiku 5.5 leads · intervals overlap

Reasoning

Like-for-like
Claude Haiku 5.5
62.6
Supported · #38/161
Qwen3.7 Plus
52.6
Supported · #67/161
Basis
BenchAlign v6.0 lane · 4 vs 2 public rows
Reading
Claude Haiku 5.5 leads · intervals overlap

Coding

Directional only
Claude Haiku 5.5
67.9
Supported · #28/180
Qwen3.7 Plus
52.4
Estimated · #72/180
Basis
BenchAlign v6.0 lane · 7 vs 7 public rows
Reading
Directional only

Multimodal

Directional only
Claude Haiku 5.5
63.9
Supported · #39/119
Qwen3.7 Plus
59.0
Estimated · #51/119
Basis
BenchAlign v6.0 lane · 4 vs 15 public rows
Reading
Directional only

Knowledge

Directional only
Claude Haiku 5.5
50.2
Supported · #84/158
Qwen3.7 Plus
52.4
Estimated · #74/158
Basis
BenchAlign v6.0 lane · 1 vs 7 public rows
Reading
Directional only

Multilingual

Directional only
Claude Haiku 5.5
56.1
Estimated · #36/88
Qwen3.7 Plus
56.2
Estimated · #30/88
Basis
BenchAlign v6.0 lane · 0 vs 5 public rows
Reading
Directional only

Instruction following

Directional only
Claude Haiku 5.5
58.3
Supported · #37/143
Qwen3.7 Plus
49.7
Estimated · #75/143
Basis
BenchAlign v6.0 lane · 0 vs 2 public rows
Reading
Directional only

Math

Directional only
Claude Haiku 5.5
62.1
Supported · #29/125
Qwen3.7 Plus
48.1
Estimated · #62/125
Basis
BenchAlign v6.0 lane · 2 vs 4 public rows
Reading
Directional only

Ranks count the models scored in each category’s BenchAlign v6.0 lane, so denominators differ by category. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

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 5.5
$0.00035
Fits in one request
Qwen3.7 Plus
API rate not published
Fits in one request

Qwen3.7 Plus has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Claude Haiku 5.5
$0.0065
Fits in one request
Qwen3.7 Plus
API rate not published
Fits in one request

Qwen3.7 Plus has no comparable published API token rate.

Cache-heavy agent loop

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

Claude Haiku 5.5
$0.009
Fits in one request
Qwen3.7 Plus
API rate not published
Fits in one request
Cached-input rate unavailable

Qwen3.7 Plus has no comparable published API token rate.

Cached input falls back to the list input rate only where a cached rate is unpublished

Price against score, among all priced models

Overall score against output price per 1M tokens, one model per family. Pricing as of November 21, 2026.

Claude Haiku 5.5

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • Claude Haiku 5.5 is on the efficiency frontier: no cheaper model scores at least as high.
  • Qwen3.7 Plus has no public API price, so it is not plotted.

Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.

See Claude Haiku 5.5 on the full price vs performance chart

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 5.5

$0.01 per 1M cached input tokens

Claude API pricing

Qwen3.7 Plus

No comparable hosted API rate

Reasoning profile

Claude Haiku 5.5

Reasoning

Qwen3.7 Plus

Reasoning

Weight access

Claude Haiku 5.5

Proprietary

Qwen3.7 Plus

Proprietary

License

Claude Haiku 5.5

Proprietary

Qwen3.7 Plus

Proprietary

Release date

Claude Haiku 5.5

2026-10-07

Qwen3.7 Plus

2026-06-03

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 Haiku 5.5 has the higher public point estimate, 63.5 versus 53.7. Their conditional score ranges do not overlap. These ranges do not establish rank confidence.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Claude Haiku 5.5 or Qwen3.7 Plus?

Claude Haiku 5.5 has the higher public point estimate, 63.5 versus 53.7. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Claude Haiku 5.5 or Qwen3.7 Plus?

Claude Haiku 5.5 scores higher for coding on the public lane, 67.9 to 52.4. Qwen3.7 Plus is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Claude Haiku 5.5 or Qwen3.7 Plus?

Claude Haiku 5.5 has the higher public agentic tasks point estimate, 68.3 to 53.8, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which costs less, Claude Haiku 5.5 or Qwen3.7 Plus?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, Claude Haiku 5.5 or Qwen3.7 Plus?

Both models list the same context window, 1M.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence79 rows

Agentic

  • Claude Haiku 5.558.62%
    Qwen3.7 Plus35.25%

    Claude Haiku 5.5 leads this result

  • Terminal-Bench 4.1

    Claude Haiku 5.540.00%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • Agents' Last Exam (Linux)

    Claude Haiku 5.557.0%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • Terminal-Bench 4.0

    Claude Haiku 5.539.20%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • HLE w/ tools

    Claude Haiku 5.557.4%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • MazeBench

    Claude Haiku 5.51%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • Hermes Index

    Claude Haiku 5.537.0%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • Hermes Bench

    Claude Haiku 5.571.0%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • OSWorld 2.1 Offline

    Claude Haiku 5.572.4%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Haiku 5.5—
    Qwen3.7 Plus70.3%
    Source

    Not directly comparable

  • QwenClawBench

    Claude Haiku 5.5—
    Qwen3.7 Plus61.8%
    Source

    Not directly comparable

  • Claw-Eval

    Claude Haiku 5.5—
    Qwen3.7 Plus62.7%
    Source

    Not directly comparable

  • BFCL v4

    Claude Haiku 5.5—
    Qwen3.7 Plus72.9%
    Source

    Not directly comparable

  • MCP Atlas

    Claude Haiku 5.5—
    Qwen3.7 Plus73.2%
    Source

    Not directly comparable

  • VITA-Bench

    Claude Haiku 5.5—
    Qwen3.7 Plus45.6%
    Source

    Not directly comparable

  • DeepPlanning

    Claude Haiku 5.5—
    Qwen3.7 Plus62.3%
    Source

    Not directly comparable

  • OSWorld-Verified

    Claude Haiku 5.5—
    Qwen3.7 Plus73.3%
    Source

    Not directly comparable

  • AndroidWorld

    Claude Haiku 5.5—
    Qwen3.7 Plus81.0%
    Source

    Not directly comparable

  • OSWorld 2.0

    Claude Haiku 5.5—
    Qwen3.7 Plus2.8%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Claude Haiku 5.5—
    Qwen3.7 Plus52.8%
    Source

    Not directly comparable

Coding

  • FrontierCode 1.1 Main

    Claude Haiku 5.546.4%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • Bug Hunt Bench

    Claude Haiku 5.521.5 fixes
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • FrontierSWE v2

    Claude Haiku 5.543.8%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • FrontierCode 2.0

    Claude Haiku 5.528.9%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • CursorBench 4.0

    Claude Haiku 5.548.4%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • VulcanBench Frontier v4

    Claude Haiku 5.592.2%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • CursorBench 4.1

    Claude Haiku 5.548.4%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Haiku 5.5—
    Qwen3.7 Plus70.3%
    Source

    Not directly comparable

  • SWE-bench Verified

    Claude Haiku 5.5—
    Qwen3.7 Plus77.7%
    Source

    Not directly comparable

  • SWE-bench Pro

    Claude Haiku 5.5—
    Qwen3.7 Plus57.6%
    Source

    Not directly comparable

  • SWE Multilingual

    Claude Haiku 5.5—
    Qwen3.7 Plus75.8%
    Source

    Not directly comparable

  • NL2Repo

    Claude Haiku 5.5—
    Qwen3.7 Plus41.1%
    Source

    Not directly comparable

  • SciCode

    Claude Haiku 5.5—
    Qwen3.7 Plus51.3%
    Source

    Not directly comparable

  • LiveCodeBench v6

    Claude Haiku 5.5—
    Qwen3.7 Plus89.6%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-1

    Claude Haiku 5.589.00%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • ARC-AGI-2

    Claude Haiku 5.561.3%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • ARC-AGI-3

    Claude Haiku 5.50.5%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • ARC-AGI-3 Provider Adapter

    Claude Haiku 5.52.82%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • CritPt

    Claude Haiku 5.5—
    Qwen3.7 Plus9.1%
    Source

    Not directly comparable

  • MRCRv2

    Claude Haiku 5.5—
    Qwen3.7 Plus91.7%
    Source

    Not directly comparable

Multimodal

  • ParseBench-2

    Claude Haiku 5.571.24%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • PerceptionBench (tools)

    Claude Haiku 5.578.6%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • ParseBench-1

    Claude Haiku 5.556.06%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • Chartography (no tools)

    Claude Haiku 5.546.4%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • MMMU-Pro

    Claude Haiku 5.5—
    Qwen3.7 Plus79%
    Source

    Not directly comparable

  • MathVision

    Claude Haiku 5.5—
    Qwen3.7 Plus90.3%
    Source

    Not directly comparable

  • CharXiv

    Claude Haiku 5.5—
    Qwen3.7 Plus85.9%
    Source

    Not directly comparable

  • ERQA

    Claude Haiku 5.5—
    Qwen3.7 Plus69.8%
    Source

    Not directly comparable

  • MedXpertQA (MM)

    Claude Haiku 5.5—
    Qwen3.7 Plus71.0%
    Source

    Not directly comparable

  • ScreenSpot Pro

    Claude Haiku 5.5—
    Qwen3.7 Plus79.0%
    Source

    Not directly comparable

  • SimpleVQA

    Claude Haiku 5.5—
    Qwen3.7 Plus81.7%
    Source

    Not directly comparable

  • MMSearch-Plus

    Claude Haiku 5.5—
    Qwen3.7 Plus41.4%
    Source

    Not directly comparable

  • RealWorldQA

    Claude Haiku 5.5—
    Qwen3.7 Plus86.9%
    Source

    Not directly comparable

  • OmniDocBench 1.5

    Claude Haiku 5.5—
    Qwen3.7 Plus91.4%
    Source

    Not directly comparable

  • OCRBench V2

    Claude Haiku 5.5—
    Qwen3.7 Plus70.7%
    Source

    Not directly comparable

  • ODINW13

    Claude Haiku 5.5—
    Qwen3.7 Plus51.1%
    Source

    Not directly comparable

  • Video-MME (with subtitle)

    Claude Haiku 5.5—
    Qwen3.7 Plus88.0%
    Source

    Not directly comparable

  • VideoMMMU

    Claude Haiku 5.5—
    Qwen3.7 Plus85.4%
    Source

    Not directly comparable

  • MLVU (M-Avg)

    Claude Haiku 5.5—
    Qwen3.7 Plus87.4%
    Source

    Not directly comparable

Knowledge

  • HLE w/o tools

    Claude Haiku 5.545.9%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • GPQA

    Claude Haiku 5.5—
    Qwen3.7 Plus90.3%
    Source

    Not directly comparable

  • GPQA-D

    Claude Haiku 5.5—
    Qwen3.7 Plus90.3%
    Source

    Not directly comparable

  • HLE

    Claude Haiku 5.5—
    Qwen3.7 Plus34.7%
    Source

    Not directly comparable

  • MMLU-Pro

    Claude Haiku 5.5—
    Qwen3.7 Plus88.5%
    Source

    Not directly comparable

  • MMLU-Redux

    Claude Haiku 5.5—
    Qwen3.7 Plus94.5%
    Source

    Not directly comparable

  • SuperGPQA

    Claude Haiku 5.5—
    Qwen3.7 Plus71.4%
    Source

    Not directly comparable

  • MMMLU

    Claude Haiku 5.5—
    Qwen3.7 Plus89.0%
    Source

    Not directly comparable

Multilingual

  • MMLU-ProX

    Claude Haiku 5.5—
    Qwen3.7 Plus85.4%
    Source

    Not directly comparable

  • NOVA-63

    Claude Haiku 5.5—
    Qwen3.7 Plus58.8%
    Source

    Not directly comparable

  • INCLUDE

    Claude Haiku 5.5—
    Qwen3.7 Plus83.0%
    Source

    Not directly comparable

  • MAXIFE

    Claude Haiku 5.5—
    Qwen3.7 Plus88.8%
    Source

    Not directly comparable

  • PolyMath

    Claude Haiku 5.5—
    Qwen3.7 Plus84.0%
    Source

    Not directly comparable

Instruction following

  • IFEval

    Claude Haiku 5.5—
    Qwen3.7 Plus94.6%
    Source

    Not directly comparable

  • IFBench

    Claude Haiku 5.5—
    Qwen3.7 Plus79.1%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    Claude Haiku 5.575.088%
    Qwen3.7 Plus34.386%

    Claude Haiku 5.5 leads this result

  • FrontierMath v2 (Tier 4)

    Claude Haiku 5.546.341%
    Source
    Qwen3.7 Plus—

    Not directly comparable

  • HMMT Feb 2026

    Claude Haiku 5.5—
    Qwen3.7 Plus92.9%
    Source

    Not directly comparable

  • IMOAnswerBench

    Claude Haiku 5.5—
    Qwen3.7 Plus86.0%
    Source

    Not directly comparable

  • Apex

    Claude Haiku 5.5—
    Qwen3.7 Plus22.7%
    Source

    Not directly comparable

79 public results · 2 shared

Watch Claude Haiku 5.5 vs Qwen3.7 Plus

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

Read a sample issue

Join 7,000+ subscribers.

Last updated November 21, 2026