Skip to main content
BenchLM
Data

Qwen3.7 Plus vs Qwen3.8-Flash-Next

Updated October 10, 2026. Rank says Qwen3.8-Flash-Next 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

Qwen3.8-Flash-Next has the higher public point estimate, 64.23 versus 55.52. Their conditional score ranges overlap. These ranges do not establish rank confidence. 14 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Alibaba logo
Qwen3.7 Plus

Alibaba

55.52/100

Supported · Public rank #61

90% interval 45.0–66.0

Model B
Alibaba logo
Qwen3.8-Flash-Next

Alibaba

64.23/100

Estimated · Public rank #37

Conditional range 49.9–78.6

Shared results
14
Qwen3.7 Plus only
38
Qwen3.8-Flash-Next only
10
Like-for-like categories
1 / 8
Supported: Qwen3.7 Plus · Estimated: Qwen3.8-Flash-Next. 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.

  • Long documents

    Prompts that approach the documented context limit

    Qwen3.7 Plus

    Qwen3.7 Plus has the larger documented context window.

    Confidence: documented
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

  • Agentic work

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

    Not enough matched evidence

    Qwen3.8-Flash-Next is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.

    Confidence: limited

  • 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.

41.2Qwen3.7 Plus52.4Qwen3.8-Flash-Next

Directional only · BenchAlign v5.8

Qwen3.8-Flash-Next 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

What is actually comparable

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

4 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, 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.

Instruction following

Like-for-like
Qwen3.7 Plus
92.8
#17/127
Qwen3.8-Flash-Next
91.2
#22/127
Basis
Provisional lane · 1 vs 1 weighted rows
Reading
Qwen3.7 Plus leads

Agentic

Directional only
Qwen3.7 Plus
35.5
Supported · #74/123
Qwen3.8-Flash-Next
59.5
Estimated · #24/123
Basis
BenchAlign v5.8 lane · 11 vs 6 public rows
Reading
Directional only

Coding

Directional only
Qwen3.7 Plus
41.2
Estimated · #60/146
Qwen3.8-Flash-Next
52.4
Supported · #37/146
Basis
BenchAlign v5.8 lane · 7 vs 5 public rows
Reading
Directional only

Multimodal

Directional only
Qwen3.7 Plus
82.0
#16/54
Qwen3.8-Flash-Next
87.7
#8/54
Basis
Provisional lane · 2 vs 1 weighted rows
Reading
Directional only

Knowledge

Directional only
Qwen3.7 Plus
54.2
Estimated · #61/177
Qwen3.8-Flash-Next
59.4
Supported · #47/177
Basis
BenchAlign v5.8 lane · 7 vs 4 public rows
Reading
Directional only

Reasoning

Not comparable
Qwen3.7 Plus
81.0
Unranked · 3 rankable rows
Qwen3.8-Flash-Next
80.9
Unranked · 2 rankable rows
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Qwen3.7 Plus
95.7
#3/17
Qwen3.8-Flash-Next
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Qwen3.7 Plus
78.7
Unranked · 3 rankable rows
Qwen3.8-Flash-Next
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, 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

Qwen3.7 Plus
API rate not published
Fits in one request
Qwen3.8-Flash-Next
Self-hosted; infrastructure cost varies
Fits in one request

Qwen3.7 Plus has no comparable published API token rate. Qwen3.8-Flash-Next has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Qwen3.7 Plus
API rate not published
Fits in one request
Qwen3.8-Flash-Next
Self-hosted; infrastructure cost varies
Fits in one request

Qwen3.7 Plus has no comparable published API token rate. Qwen3.8-Flash-Next has no comparable published API token rate.

Cache-heavy agent loop

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

Qwen3.7 Plus
API rate not published
Fits in one request
Cached-input rate unavailable
Qwen3.8-Flash-Next
Self-hosted; infrastructure cost varies
Fits in one request
Cached-input rate unavailable

Qwen3.7 Plus has no comparable published API token rate. Qwen3.8-Flash-Next 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.

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Qwen3.7 Plus

No comparable hosted API rate

Qwen3.8-Flash-Next

No comparable hosted API rate

Qwen3.8-Flash-Next model card

Documented inputs

Qwen3.7 Plus

Not sourced

Qwen3.8-Flash-Next

Not sourced

Documented outputs

Qwen3.7 Plus

Not sourced

Qwen3.8-Flash-Next

Not sourced

Provider availability

Qwen3.7 Plus

Not sourced

Qwen3.8-Flash-Next

Not sourced

Reasoning profile

Qwen3.7 Plus

Reasoning

Qwen3.8-Flash-Next

Reasoning

Weight access

Qwen3.7 Plus

Proprietary

Qwen3.8-Flash-Next

Open Weight

License

Qwen3.7 Plus

Proprietary

Qwen3.8-Flash-Next

Open Weight

Release date

Qwen3.7 Plus

2026-06-03

Qwen3.8-Flash-Next

2026-08-26

If you already use one of these models

Deployment change
Both entries list Alibaba as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
Quality signal
Qwen3.8-Flash-Next has the higher public point estimate, 64.23 versus 55.52. Their conditional score ranges overlap. These ranges do not establish rank confidence.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Qwen3.7 Plus has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Qwen3.7 Plus or Qwen3.8-Flash-Next?

Qwen3.8-Flash-Next has the higher public point estimate, 64.23 versus 55.52. Their conditional score ranges 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, Qwen3.7 Plus or Qwen3.8-Flash-Next?

Qwen3.8-Flash-Next scores higher for coding on the public lane, 52.4 to 41.2. 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, Qwen3.7 Plus or Qwen3.8-Flash-Next?

Qwen3.8-Flash-Next scores higher for agentic tasks on the public lane, 59.5 to 35.5. Qwen3.8-Flash-Next is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which costs less, Qwen3.7 Plus or Qwen3.8-Flash-Next?

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, Qwen3.7 Plus or Qwen3.8-Flash-Next?

Qwen3.7 Plus has the larger documented context window: 1M, compared with 262K.

Benchmark evidence

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

Browse raw public benchmark evidence62 rows

Agentic

  • Terminal-Bench 2.0

    Qwen3.7 Plus70.3%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • QwenClawBench

    Qwen3.7 Plus61.8%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • Claw-Eval

    Qwen3.7 Plus62.7%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • BFCL v4

    Qwen3.7 Plus72.9%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • MCP Atlas

    Qwen3.7 Plus73.2%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • VITA-Bench

    Qwen3.7 Plus45.6%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • DeepPlanning

    Qwen3.7 Plus62.3%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • OSWorld-Verified

    Qwen3.7 Plus73.3%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • AndroidWorld

    Qwen3.7 Plus81.0%
    Source
    Qwen3.8-Flash-Next84.5%
    Source

    Qwen3.8-Flash-Next leads this result

  • OSWorld 2.0

    Qwen3.7 Plus2.8%
    Source
    Qwen3.8-Flash-Next19.4%
    Source

    Qwen3.8-Flash-Next leads this result

  • Terminal-Bench 2.1 (Vals)

    Qwen3.7 Plus52.8%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • CoWorkBench

    Qwen3.7 Plus—
    Qwen3.8-Flash-Next73.9%
    Source

    Not directly comparable

  • JobBench

    Qwen3.7 Plus—
    Qwen3.8-Flash-Next55.7%
    Source

    Not directly comparable

  • Agents' Last Exam

    Qwen3.7 Plus—
    Qwen3.8-Flash-Next51.2%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Qwen3.7 Plus—
    Qwen3.8-Flash-Next73.5%
    Source

    Not directly comparable

Coding

  • Terminal-Bench 2.0

    Qwen3.7 Plus70.3%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • SWE-bench Verified

    Qwen3.7 Plus77.7%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • SWE-bench Pro

    Qwen3.7 Plus57.6%
    Source
    Qwen3.8-Flash-Next62.5%
    Source

    Qwen3.8-Flash-Next leads this result

  • SWE Multilingual

    Qwen3.7 Plus75.8%
    Source
    Qwen3.8-Flash-Next81%
    Source

    Qwen3.8-Flash-Next leads this result

  • NL2Repo

    Qwen3.7 Plus41.1%
    Source
    Qwen3.8-Flash-Next48.1%
    Source

    Qwen3.8-Flash-Next leads this result

  • SciCode

    Qwen3.7 Plus51.3%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • LiveCodeBench v6

    Qwen3.7 Plus89.6%
    Source
    Qwen3.8-Flash-Next91.9%
    Source

    Qwen3.8-Flash-Next leads this result

  • DeepSWE

    Qwen3.7 Plus—
    Qwen3.8-Flash-Next58.7%
    Source

    Not directly comparable

Reasoning

  • CritPt

    Qwen3.7 Plus9.1%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • MRCRv2

    Qwen3.7 Plus91.7%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

Multimodal

  • MMMU-Pro

    Qwen3.7 Plus79%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • MathVision

    Qwen3.7 Plus90.3%
    Source
    Qwen3.8-Flash-Next90.6%
    Source

    Qwen3.8-Flash-Next leads this result

  • CharXiv

    Qwen3.7 Plus85.9%
    Source
    Qwen3.8-Flash-Next90.6%
    Source

    Qwen3.8-Flash-Next leads this result

  • ERQA

    Qwen3.7 Plus69.8%
    Source
    Qwen3.8-Flash-Next72.3%
    Source

    Qwen3.8-Flash-Next leads this result

  • MedXpertQA (MM)

    Qwen3.7 Plus71.0%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • ScreenSpot Pro

    Qwen3.7 Plus79.0%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • SimpleVQA

    Qwen3.7 Plus81.7%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • MMSearch-Plus

    Qwen3.7 Plus41.4%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • RealWorldQA

    Qwen3.7 Plus86.9%
    Source
    Qwen3.8-Flash-Next88.5%
    Source

    Qwen3.8-Flash-Next leads this result

  • OmniDocBench 1.5

    Qwen3.7 Plus91.4%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • OCRBench V2

    Qwen3.7 Plus70.7%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • ODINW13

    Qwen3.7 Plus51.1%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • Video-MME (with subtitle)

    Qwen3.7 Plus88.0%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • VideoMMMU

    Qwen3.7 Plus85.4%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • MLVU (M-Avg)

    Qwen3.7 Plus87.4%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • Vision2Web

    Qwen3.7 Plus—
    Qwen3.8-Flash-Next64.0%
    Source

    Not directly comparable

  • LVBench

    Qwen3.7 Plus—
    Qwen3.8-Flash-Next76.6%
    Source

    Not directly comparable

  • MathVision w/ Python

    Qwen3.7 Plus—
    Qwen3.8-Flash-Next95.7%
    Source

    Not directly comparable

  • CharXiv w/o tools

    Qwen3.7 Plus—
    Qwen3.8-Flash-Next84.6%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Qwen3.7 Plus90.3%
    Source
    Qwen3.8-Flash-Next91.7%
    Source

    Qwen3.8-Flash-Next leads this result

  • GPQA-D

    Qwen3.7 Plus90.3%
    Source
    Qwen3.8-Flash-Next91.7%
    Source

    Qwen3.8-Flash-Next leads this result

  • HLE

    Qwen3.7 Plus34.7%
    Source
    Qwen3.8-Flash-Next35.9%
    Source

    Qwen3.8-Flash-Next leads this result

  • MMLU-Pro

    Qwen3.7 Plus88.5%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • MMLU-Redux

    Qwen3.7 Plus94.5%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • SuperGPQA

    Qwen3.7 Plus71.4%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • MMMLU

    Qwen3.7 Plus89.0%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • HLE w/o tools

    Qwen3.7 Plus—
    Qwen3.8-Flash-Next35.9%
    Source

    Not directly comparable

Multilingual

  • MMLU-ProX

    Qwen3.7 Plus85.4%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • NOVA-63

    Qwen3.7 Plus58.8%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • INCLUDE

    Qwen3.7 Plus83.0%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • MAXIFE

    Qwen3.7 Plus88.8%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • PolyMath

    Qwen3.7 Plus84.0%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

Instruction following

  • IFEval

    Qwen3.7 Plus94.6%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • IFBench

    Qwen3.7 Plus79.1%
    Source
    Qwen3.8-Flash-Next81.3%
    Source

    Qwen3.8-Flash-Next leads this result

Math

  • HMMT Feb 2026

    Qwen3.7 Plus92.9%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • IMOAnswerBench

    Qwen3.7 Plus86.0%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • Apex

    Qwen3.7 Plus22.7%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

62 public results · 14 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch Qwen3.7 Plus vs Qwen3.8-Flash-Next

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

Read a sample issue

Join 5,500+ readers.

Last updated October 10, 2026