Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

Pareto 26.9 vs Qwen3.8-Flash-Next

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.

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
Pareto 26.9

Unbiased

—

Evidence status unavailable

90% interval unavailable

Alibaba logo
Model B
Qwen3.8-Flash-Next

Alibaba

56.98/100

Estimated · Public rank #84

90% interval 45.5–68.5

Updated September 18, 2026. We do not rank this pair: at least one has no public score. Public scores include evidence status and uncertainty.

Share or export

Share on XLinkedInSocial cardCSVJSON

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.

No workload recommendation clears the current evidence threshold.

Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.

Show secondary and unsupported calls

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Pareto 26.9 is not ranked on the public lane for coding, so no winner is named for coding.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    Pareto 26.9 is not ranked on the public lane for agentic, so no winner is named for agentic.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    Not enough matched evidence

    A complete context comparison is not sourced.

    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

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
Pareto 26.9 only
2
Qwen3.8-Flash-Next only
22
Like-for-like categories
0 / 8

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign 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.

Agentic

Not comparable
Pareto 26.9
Not ranked
Qwen3.8-Flash-Next
58.8
Estimated · #29/154
Basis
BenchAlign lane · 1 vs 6 public rows
Reading
Not comparable

Coding

Not comparable
Pareto 26.9
Not ranked
Qwen3.8-Flash-Next
57.9
Supported · #30/154
Basis
BenchAlign lane · 1 vs 5 public rows
Reading
Not comparable

Reasoning

Not comparable
Pareto 26.9
Not ranked
Qwen3.8-Flash-Next
75.8
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Knowledge

Not comparable
Pareto 26.9
Not ranked
Qwen3.8-Flash-Next
55.6
Supported · #53/184
Basis
BenchAlign lane · 1 vs 4 public rows
Reading
Not comparable

Math

Not comparable
Pareto 26.9
Not ranked
Qwen3.8-Flash-Next
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Pareto 26.9
Not ranked
Qwen3.8-Flash-Next
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Pareto 26.9
Not ranked
Qwen3.8-Flash-Next
83.1
#7/48
Basis
Provisional lane · 1 vs 1 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Pareto 26.9
Not ranked
Qwen3.8-Flash-Next
87.2
#33/124
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

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

Pareto 26.9
$0.00625
Fit state unavailable
Qwen3.8-Flash-Next
Self-hosted; infrastructure cost varies
Fits in one request

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

Repository review

50K fresh input + 3K output tokens

Pareto 26.9
$0.1475
Fit state unavailable
Qwen3.8-Flash-Next
Self-hosted; infrastructure cost varies
Fits in one request

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

Cache-heavy agent loop

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

Pareto 26.9
$0.175
Fit state unavailable
Qwen3.8-Flash-Next
Self-hosted; infrastructure cost varies
Fits in one request
Cached-input rate unavailable

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

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.

Pareto 26.9

$0.25 per 1M cached input tokens

Unbiased pricing

Qwen3.8-Flash-Next

No comparable hosted API rate

Qwen3.8-Flash-Next model card

Documented inputs

Pareto 26.9

Not sourced

Qwen3.8-Flash-Next

Not sourced

Documented outputs

Pareto 26.9

Not sourced

Qwen3.8-Flash-Next

Not sourced

Provider availability

Pareto 26.9

Not sourced

Qwen3.8-Flash-Next

Not sourced

Reasoning profile

Pareto 26.9

Reasoning

Qwen3.8-Flash-Next

Reasoning

Weight access

Pareto 26.9

Proprietary

Qwen3.8-Flash-Next

Open Weight

License

Pareto 26.9

Proprietary

Qwen3.8-Flash-Next

Open Weight

Release date

Pareto 26.9

2026-09-17

Qwen3.8-Flash-Next

2026-08-26

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
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
A complete documented context comparison is not available.

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 evidence26 rows

Agentic

  • Terminal-Bench 4.0

    Pareto 26.951.00%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • CoWorkBench

    Pareto 26.9—
    Qwen3.8-Flash-Next73.9%
    Source

    Not directly comparable

  • JobBench

    Pareto 26.9—
    Qwen3.8-Flash-Next55.7%
    Source

    Not directly comparable

  • Agents' Last Exam

    Pareto 26.9—
    Qwen3.8-Flash-Next51.2%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Pareto 26.9—
    Qwen3.8-Flash-Next73.5%
    Source

    Not directly comparable

  • AndroidWorld

    Pareto 26.9—
    Qwen3.8-Flash-Next84.5%
    Source

    Not directly comparable

  • OSWorld 2.0

    Pareto 26.9—
    Qwen3.8-Flash-Next19.4%
    Source

    Not directly comparable

Coding

  • DeepSWE

    Pareto 26.974.0%
    Source
    Qwen3.8-Flash-Next58.7%
    Source

    Pareto 26.9 leads this result

  • SWE-bench Pro

    Pareto 26.9—
    Qwen3.8-Flash-Next62.5%
    Source

    Not directly comparable

  • SWE Multilingual

    Pareto 26.9—
    Qwen3.8-Flash-Next81%
    Source

    Not directly comparable

  • NL2Repo

    Pareto 26.9—
    Qwen3.8-Flash-Next48.1%
    Source

    Not directly comparable

  • LiveCodeBench v6

    Pareto 26.9—
    Qwen3.8-Flash-Next91.9%
    Source

    Not directly comparable

Knowledge

  • HLE w/o tools

    Pareto 26.949%
    Source
    Qwen3.8-Flash-Next35.9%
    Source

    Pareto 26.9 leads this result

  • GPQA

    Pareto 26.9—
    Qwen3.8-Flash-Next91.7%
    Source

    Not directly comparable

  • GPQA-D

    Pareto 26.9—
    Qwen3.8-Flash-Next91.7%
    Source

    Not directly comparable

  • HLE

    Pareto 26.9—
    Qwen3.8-Flash-Next35.9%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    Pareto 26.978%
    Source
    Qwen3.8-Flash-Next—

    Not directly comparable

  • Vision2Web

    Pareto 26.9—
    Qwen3.8-Flash-Next64.0%
    Source

    Not directly comparable

  • ERQA

    Pareto 26.9—
    Qwen3.8-Flash-Next72.3%
    Source

    Not directly comparable

  • LVBench

    Pareto 26.9—
    Qwen3.8-Flash-Next76.6%
    Source

    Not directly comparable

  • RealWorldQA

    Pareto 26.9—
    Qwen3.8-Flash-Next88.5%
    Source

    Not directly comparable

  • MathVision

    Pareto 26.9—
    Qwen3.8-Flash-Next90.6%
    Source

    Not directly comparable

  • MathVision w/ Python

    Pareto 26.9—
    Qwen3.8-Flash-Next95.7%
    Source

    Not directly comparable

  • CharXiv w/o tools

    Pareto 26.9—
    Qwen3.8-Flash-Next84.6%
    Source

    Not directly comparable

  • CharXiv

    Pareto 26.9—
    Qwen3.8-Flash-Next90.6%
    Source

    Not directly comparable

Instruction following

  • IFBench

    Pareto 26.9—
    Qwen3.8-Flash-Next81.3%
    Source

    Not directly comparable

Questions

Which is better, Pareto 26.9 or Qwen3.8-Flash-Next?

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, Pareto 26.9 or Qwen3.8-Flash-Next?

Pareto 26.9 is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Pareto 26.9 or Qwen3.8-Flash-Next?

Pareto 26.9 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Pareto 26.9 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, Pareto 26.9 or Qwen3.8-Flash-Next?

A complete documented context-window comparison is not available.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 18, 2026

Watch Pareto 26.9 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 2,000+ readers.