Skip to main content
BenchLM
Data

Claude Sonnet 5.5 vs Qwen3.8 Max

Updated November 12, 2026. Rank says Claude Sonnet 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 Sonnet 5.5 has the higher public score, 83.07 versus 63.59, and the 90% score intervals do not overlap. 13 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
Claude Sonnet 5.5

Anthropic

83.07/100

Supported · Public rank #6

90% interval 78.8–87.3

Model B
Alibaba logo
Qwen3.8 Max

Alibaba

63.59/100

Supported · Public rank #35

90% interval 54.9–72.3

API price per 1M tokens

Claude Sonnet 5.5: $2 input / $10 output

Qwen3.8 Max: No comparable API price

Context window

Claude Sonnet 5.5: 1M

Qwen3.8 Max: 1M

Released

Claude Sonnet 5.5: September 28, 2026

Qwen3.8 Max: August 3, 2026

Shared results
13
Claude Sonnet 5.5 only
51
Qwen3.8 Max only
55
Like-for-like categories
3 / 8
Supported: Claude Sonnet 5.5 and Qwen3.8 MaxHow 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.

  • Coding work

    Code generation, repair, and software-engineering tasks

    Claude Sonnet 5.5

    Claude Sonnet 5.5 has the higher public coding point estimate, 81 to 50.9, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited

  • Agentic work

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

    Claude Sonnet 5.5

    Claude Sonnet 5.5 has the higher public agentic point estimate, 72.7 to 64.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited
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

    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.

81.0Claude Sonnet 5.550.9Qwen3.8 Max

Like-for-like · BenchAlign v5.8

Claude Sonnet 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.

Open the coding leaderboardShortlist models for this job
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.

2 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.

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 v5.8 lane for agentic, coding, reasoning, multimodal, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Like-for-like
Claude Sonnet 5.5
72.7
Supported · #9/135
Qwen3.8 Max
64.6
Supported · #19/135
Basis
BenchAlign v5.8 lane · 19 vs 19 public rows
Reading
Claude Sonnet 5.5 leads · intervals overlap

Coding

Like-for-like
Claude Sonnet 5.5
81.0
Supported · #4/162
Qwen3.8 Max
50.9
Supported · #43/162
Basis
BenchAlign v5.8 lane · 12 vs 14 public rows
Reading
Claude Sonnet 5.5 leads

Knowledge

Like-for-like
Claude Sonnet 5.5
82.1
Supported · #6/180
Qwen3.8 Max
65.3
Supported · #27/180
Basis
BenchAlign v5.8 lane · 17 vs 6 public rows
Reading
Claude Sonnet 5.5 leads · intervals overlap

Reasoning

Directional only
Claude Sonnet 5.5
77.0
Supported · #6/160
Qwen3.8 Max
60.5
Estimated · #30/160
Basis
BenchAlign v5.8 lane · 0 vs 2 public rows
Reading
Directional only

Multimodal

Directional only
Claude Sonnet 5.5
78.9
Estimated · #7/67
Qwen3.8 Max
65.7
Estimated · #25/67
Basis
BenchAlign v5.8 lane · 10 vs 24 public rows
Reading
Directional only

Multilingual

Not comparable
Claude Sonnet 5.5
Not ranked
Qwen3.8 Max
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Claude Sonnet 5.5
Not ranked
Qwen3.8 Max
94.7
#2/157
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Math

Not comparable
Claude Sonnet 5.5
89.7
Unranked · 4 rankable rows
Qwen3.8 Max
74.1
Unranked · 2 rankable rows
Basis
Provisional lane · 2 vs 2 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, reasoning, multimodal, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. 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 Sonnet 5.5
$0.007
Fits in one request
Qwen3.8 Max
API rate not published
Fits in one request

Qwen3.8 Max has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Claude Sonnet 5.5
$0.13
Fits in one request
Qwen3.8 Max
API rate not published
Fits in one request

Qwen3.8 Max has no comparable published API token rate.

Cache-heavy agent loop

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

Claude Sonnet 5.5
$0.16
Fits in one request
Qwen3.8 Max
API rate not published
Fits in one request
Cached-input rate unavailable

Qwen3.8 Max has no comparable published API token rate.

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

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Reasoning profile

Claude Sonnet 5.5

Reasoning

Qwen3.8 Max

Reasoning

Weight access

Claude Sonnet 5.5

Proprietary

Qwen3.8 Max

Open Weight

License

Claude Sonnet 5.5

Proprietary

Qwen3.8 Max

Open Weight

Release date

Claude Sonnet 5.5

2026-09-28

Qwen3.8 Max

2026-08-03

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 Sonnet 5.5 has the higher public score, 83.07 versus 63.59, and the 90% score intervals do not overlap.
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 Sonnet 5.5 or Qwen3.8 Max?

Claude Sonnet 5.5 has the higher public score, 83.07 versus 63.59, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.

Which is better for coding, Claude Sonnet 5.5 or Qwen3.8 Max?

Claude Sonnet 5.5 has the higher public coding point estimate, 81 to 50.9, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which is better for agentic tasks, Claude Sonnet 5.5 or Qwen3.8 Max?

Claude Sonnet 5.5 has the higher public agentic tasks point estimate, 72.7 to 64.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which costs less, Claude Sonnet 5.5 or Qwen3.8 Max?

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 Sonnet 5.5 or Qwen3.8 Max?

Both models list the same context window, 1M.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Claude Sonnet 5.5
API / mo$9,000
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Qwen3.8 Max
API / mo (DeepInfra)$4,951
Self-host / mo$57,606
Break-evenNot reached at 70% load
Model the full break-even

Benchmark evidence

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

Browse raw public benchmark evidence119 rows

Agentic

  • Terminal-Bench 4.1

    Claude Sonnet 5.563.90%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Terminal-Bench 4.0

    Claude Sonnet 5.570.60%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • HLE w/ tools

    Claude Sonnet 5.564.5%
    Source
    Qwen3.8 Max56.2%
    Source

    Claude Sonnet 5.5 leads this result

  • DRACO

    Claude Sonnet 5.587.0%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Terminal-Bench-Science 0.1

    Claude Sonnet 5.559.9%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • LAB all-pass (Harvey held-out)

    Claude Sonnet 5.510.0%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • LAB criterion-pass (Harvey held-out)

    Claude Sonnet 5.593.1%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Toolathlon Verified Pass@3

    Claude Sonnet 5.585.2%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Toolathlon Verified Pass³

    Claude Sonnet 5.568.5%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Toolathlon Verified avg. turns

    Claude Sonnet 5.531.6 turns
    Source
    Qwen3.8 Max—

    Not directly comparable

  • AutomationBench (Zapier 1.0.6)

    Claude Sonnet 5.544.70%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Toolathlon-Verified

    Claude Sonnet 5.577.8%
    Source
    Qwen3.8 Max72.5%
    Source

    Claude Sonnet 5.5 leads this result

  • Hermes Index

    Shared source
    Claude Sonnet 5.553.1%
    Qwen3.8 Max36.2%

    Claude Sonnet 5.5 leads this result

  • Hermes Bench

    Shared source
    Claude Sonnet 5.573.5%
    Qwen3.8 Max70.5%

    Claude Sonnet 5.5 leads this result

  • MazeBench

    Claude Sonnet 5.58%
    Source
    Qwen3.8 Max0%
    Source

    Claude Sonnet 5.5 leads this result

  • OSWorld 2.1

    Claude Sonnet 5.580.1%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • OSWorld 2.1 Offline

    Claude Sonnet 5.583.9%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Binary Exploitation Benchmark

    Claude Sonnet 5.548
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Claude Sonnet 5.583.1%
    Source
    Qwen3.8 Max67.4%
    Source

    Claude Sonnet 5.5 leads this result

  • Terminal-Bench 2.1

    Claude Sonnet 5.5—
    Qwen3.8 Max86.6%
    Source

    Not directly comparable

  • CoWorkBench

    Claude Sonnet 5.5—
    Qwen3.8 Max74.8%
    Source

    Not directly comparable

  • JobBench

    Claude Sonnet 5.5—
    Qwen3.8 Max53.4%
    Source

    Not directly comparable

  • skillsBench

    Claude Sonnet 5.5—
    Qwen3.8 Max70.2%
    Source

    Not directly comparable

  • Agents' Last Exam

    Claude Sonnet 5.5—
    Qwen3.8 Max52.4%
    Source

    Not directly comparable

  • AutomationBench

    Claude Sonnet 5.5—
    Qwen3.8 Max27.3%
    Source

    Not directly comparable

  • WideResearch

    Claude Sonnet 5.5—
    Qwen3.8 Max81.9%
    Source

    Not directly comparable

  • OSWorld-Verified

    Claude Sonnet 5.5—
    Qwen3.8 Max86.1%
    Source

    Not directly comparable

  • OSWorld 2.0

    Claude Sonnet 5.5—
    Qwen3.8 Max19.4%
    Source

    Not directly comparable

  • WebArena-Verified

    Claude Sonnet 5.5—
    Qwen3.8 Max66.8%
    Source

    Not directly comparable

  • AndroidWorld

    Claude Sonnet 5.5—
    Qwen3.8 Max85.3%
    Source

    Not directly comparable

  • MobileWorld

    Claude Sonnet 5.5—
    Qwen3.8 Max77.8%
    Source

    Not directly comparable

  • CWE-bench

    Claude Sonnet 5.5—
    Qwen3.8 Max45.4%
    Source

    Not directly comparable

Coding

  • FrontierCode 1.1 Main

    Claude Sonnet 5.546.2%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • CursorBench 4.0

    Claude Sonnet 5.555.5%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • SWE-bench Pro

    Claude Sonnet 5.581.3%
    Source
    Qwen3.8 Max67.7%
    Source

    Claude Sonnet 5.5 leads this result

  • SWE Multilingual

    Claude Sonnet 5.590.3%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • SWE Multimodal

    Claude Sonnet 5.554.3%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • DeepSWE

    Claude Sonnet 5.571.0%
    Source
    Qwen3.8 Max56.6%
    Source

    Claude Sonnet 5.5 leads this result

  • FrontierCode 1.1 Extended

    Claude Sonnet 5.559.1%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • ProgramBench

    Claude Sonnet 5.579.7%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • FrontierSWE v2

    Shared source
    Claude Sonnet 5.561.9%
    Qwen3.8 Max15.8%

    Claude Sonnet 5.5 leads this result

  • Bug Hunt Bench

    Shared source
    Claude Sonnet 5.551.3 fixes
    Qwen3.8 Max25.7 fixes

    Claude Sonnet 5.5 leads this result

  • FrontierCode 2.0

    Claude Sonnet 5.541.0%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • VulcanBench Frontier v4

    Claude Sonnet 5.592.0%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Terminal-Bench 2.1

    Claude Sonnet 5.5—
    Qwen3.8 Max86.6%
    Source

    Not directly comparable

  • NL2Repo

    Claude Sonnet 5.5—
    Qwen3.8 Max55.9%
    Source

    Not directly comparable

  • FrontierSWE

    Claude Sonnet 5.5—
    Qwen3.8 Max73.5%
    Source

    Not directly comparable

  • MLS-Bench Lite

    Claude Sonnet 5.5—
    Qwen3.8 Max41.0%
    Source

    Not directly comparable

  • PaperBench

    Claude Sonnet 5.5—
    Qwen3.8 Max93.0%
    Source

    Not directly comparable

  • VulcanBench v3

    Claude Sonnet 5.5—
    Qwen3.8 Max81.2%
    Source

    Not directly comparable

  • OpenHarmony Bench

    Claude Sonnet 5.5—
    Qwen3.8 Max60.8%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    Claude Sonnet 5.5—
    Qwen3.8 Max87.9%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    Claude Sonnet 5.5—
    Qwen3.8 Max85.6%
    Source

    Not directly comparable

  • ScarfBench

    Claude Sonnet 5.5—
    Qwen3.8 Max63.7%
    Source

    Not directly comparable

Reasoning

  • MRCRv2

    Claude Sonnet 5.5—
    Qwen3.8 Max92.9%
    Source

    Not directly comparable

  • LongBench v2

    Claude Sonnet 5.5—
    Qwen3.8 Max66.3%
    Source

    Not directly comparable

Multimodal

  • ExtractBench Pro

    Claude Sonnet 5.532%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • ExtractBench (LlamaIndex)

    Claude Sonnet 5.594.68%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • ParseBench

    Claude Sonnet 5.569.21%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Chartography (no tools)

    Claude Sonnet 5.561.6%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Chartography (tools)

    Claude Sonnet 5.590.2%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • BenchCAD Vision2Code (no tools)

    Claude Sonnet 5.50.747
    Source
    Qwen3.8 Max—

    Not directly comparable

  • BenchCAD Vision2Code (tools)

    Claude Sonnet 5.50.963
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Biomedical image analysis

    Claude Sonnet 5.572.2%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • OfficeQA

    Claude Sonnet 5.576.9%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • OfficeQA Pro

    Claude Sonnet 5.565.6%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • MMMU-Pro

    Claude Sonnet 5.5—
    Qwen3.8 Max82.3%
    Source

    Not directly comparable

  • MathVision

    Claude Sonnet 5.5—
    Qwen3.8 Max95.2%
    Source

    Not directly comparable

  • MathVision w/ Python

    Claude Sonnet 5.5—
    Qwen3.8 Max97.7%
    Source

    Not directly comparable

  • BabyVision

    Claude Sonnet 5.5—
    Qwen3.8 Max82.0%
    Source

    Not directly comparable

  • BabyVision w/ Python

    Claude Sonnet 5.5—
    Qwen3.8 Max91.3%
    Source

    Not directly comparable

  • ZeroBench

    Claude Sonnet 5.5—
    Qwen3.8 Max24.0%
    Source

    Not directly comparable

  • ZeroBench w/ Python

    Claude Sonnet 5.5—
    Qwen3.8 Max49.0%
    Source

    Not directly comparable

  • MedXpertQA (MM)

    Claude Sonnet 5.5—
    Qwen3.8 Max80.4%
    Source

    Not directly comparable

  • ScreenSpot Pro

    Claude Sonnet 5.5—
    Qwen3.8 Max84.5%
    Source

    Not directly comparable

  • Vision2Web

    Claude Sonnet 5.5—
    Qwen3.8 Max69.0%
    Source

    Not directly comparable

  • CharXiv w/o tools

    Claude Sonnet 5.5—
    Qwen3.8 Max88.4%
    Source

    Not directly comparable

  • CharXiv

    Claude Sonnet 5.5—
    Qwen3.8 Max93.5%
    Source

    Not directly comparable

  • OmniDocBench 1.5

    Claude Sonnet 5.5—
    Qwen3.8 Max92.1%
    Source

    Not directly comparable

  • OCRBench V2

    Claude Sonnet 5.5—
    Qwen3.8 Max74.2%
    Source

    Not directly comparable

  • CC-OCR

    Claude Sonnet 5.5—
    Qwen3.8 Max79.6%
    Source

    Not directly comparable

  • RealWorldQA

    Claude Sonnet 5.5—
    Qwen3.8 Max88.0%
    Source

    Not directly comparable

  • ERQA

    Claude Sonnet 5.5—
    Qwen3.8 Max77.8%
    Source

    Not directly comparable

  • SimpleVQA

    Claude Sonnet 5.5—
    Qwen3.8 Max75.0%
    Source

    Not directly comparable

  • PerceptionBench

    Claude Sonnet 5.5—
    Qwen3.8 Max63.5%
    Source

    Not directly comparable

  • Video-MME (with subtitle)

    Claude Sonnet 5.5—
    Qwen3.8 Max90.4%
    Source

    Not directly comparable

  • VideoMMMU

    Claude Sonnet 5.5—
    Qwen3.8 Max88.7%
    Source

    Not directly comparable

  • MMVU

    Claude Sonnet 5.5—
    Qwen3.8 Max82.4%
    Source

    Not directly comparable

  • MLVU (M-Avg)

    Claude Sonnet 5.5—
    Qwen3.8 Max90.8%
    Source

    Not directly comparable

  • LVBench

    Claude Sonnet 5.5—
    Qwen3.8 Max81.8%
    Source

    Not directly comparable

Knowledge

  • HealthBench (raw)

    Claude Sonnet 5.569.4%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • HealthBench (length-adjusted)

    Claude Sonnet 5.565.4%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • HealthBench Professional (raw)

    Claude Sonnet 5.577.1%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • HealthBench Professional

    Claude Sonnet 5.569.2%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • BioMysteryBench (human-solvable)

    Claude Sonnet 5.589.2%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • BioMysteryBench (human-difficult)

    Claude Sonnet 5.544.7%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • SpatialBench Verified

    Claude Sonnet 5.572.5%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • SingleCellBench

    Claude Sonnet 5.559.1%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Protein Design

    Claude Sonnet 5.551.0%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Morphology-to-molecule matching

    Claude Sonnet 5.525.0%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Medicinal chemistry

    Claude Sonnet 5.565.3%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Protein Design library ranking

    Claude Sonnet 5.554.8%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • De novo protein-binder design

    Claude Sonnet 5.582.3%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Protocols (troubleshooting)

    Claude Sonnet 5.567.3%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Protocols (understanding)

    Claude Sonnet 5.566.6%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • HLE w/o tools

    Claude Sonnet 5.556.9%
    Source
    Qwen3.8 Max43.6%
    Source

    Claude Sonnet 5.5 leads this result

  • PhysicianBench

    Claude Sonnet 5.563.2%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • GPQA

    Claude Sonnet 5.5—
    Qwen3.8 Max92.6%
    Source

    Not directly comparable

  • GPQA-D

    Claude Sonnet 5.5—
    Qwen3.8 Max92.6%
    Source

    Not directly comparable

  • HLE

    Claude Sonnet 5.5—
    Qwen3.8 Max43.6%
    Source

    Not directly comparable

  • GPQA Diamond (Vals)

    Claude Sonnet 5.5—
    Qwen3.8 Max93.7%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    Claude Sonnet 5.5—
    Qwen3.8 Max88.6%
    Source

    Not directly comparable

Multilingual

  • GMMLU

    Claude Sonnet 5.592.1%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • MILU

    Claude Sonnet 5.591.6%
    Source
    Qwen3.8 Max—

    Not directly comparable

Instruction following

  • IFBench

    Claude Sonnet 5.5—
    Qwen3.8 Max82.8%
    Source

    Not directly comparable

Math

  • ArXivMath Aug. 2026 (no tools)

    Claude Sonnet 5.586.8%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • ArXivMath Aug. 2026 (tools)

    Claude Sonnet 5.595.2%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    Claude Sonnet 5.588.772%
    Qwen3.8 Max74.737%

    Claude Sonnet 5.5 leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    Claude Sonnet 5.580.488%
    Qwen3.8 Max46.341%

    Claude Sonnet 5.5 leads this result

119 public results · 13 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch Claude Sonnet 5.5 vs Qwen3.8 Max

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 12, 2026