Skip to main content
BenchLM
Data

Jev 1.14 vs Qwen3.5 397B

Updated October 20, 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 XLinkedInAPI/MCP

Decision reading

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead. 0 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Jev 1.14

TypeSafe AI

—

Evidence status unavailable

90% interval unavailable

Model B
Alibaba logo
Qwen3.5 397B

Alibaba

55.39/100

Estimated · Public rank #66

Conditional range 41.0–69.7

Shared results
0
Jev 1.14 only
0
Qwen3.5 397B only
62
Like-for-like categories
0 / 8
Estimated: Qwen3.5 397B. 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

    Qwen3.5 397B

    Qwen3.5 397B has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    Jev 1.14

    Jev 1.14 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

    Jev 1.14

    Jev 1.14 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

    Jev 1.14 and Qwen3.5 397B are 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

    Jev 1.14 is not ranked on the public lane for agentic, so no winner is named for agentic.

    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. Jev 1.14 does not fit this workload in one request. Qwen3.5 397B does not fit this workload in one request. Jev 1.14 has no published cached-input rate, so cached tokens use its listed input rate. Qwen3.5 397B has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback

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.

—Jev 1.14—Qwen3.5 397B

Not comparable · BenchAlign v5.8

The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.

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.

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.

A shared-evidence shape is not available.

BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.

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.

Agentic

Not comparable
Jev 1.14
Not ranked
Qwen3.5 397B
44.2
Estimated · #62/131
Basis
BenchAlign v5.8 lane · 0 vs 14 public rows
Reading
Not comparable

Coding

Not comparable
Jev 1.14
Not ranked
Qwen3.5 397B
Not ranked
Basis
BenchAlign v5.8 lane · 0 vs 6 public rows
Reading
Not comparable

Reasoning

Not comparable
Jev 1.14
Not ranked
Qwen3.5 397B
74.1
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Jev 1.14
Not ranked
Qwen3.5 397B
73.6
#29/55
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Knowledge

Not comparable
Jev 1.14
Not ranked
Qwen3.5 397B
53.2
Estimated · #70/187
Basis
BenchAlign v5.8 lane · 0 vs 6 public rows
Reading
Not comparable

Multilingual

Not comparable
Jev 1.14
Not ranked
Qwen3.5 397B
93.8
#5/17
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Jev 1.14
Not ranked
Qwen3.5 397B
79.9
#59/149
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Math

Not comparable
Jev 1.14
Not ranked
Qwen3.5 397B
81.7
Unranked · 5 rankable rows
Basis
Provisional lane · 0 vs 2 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.

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

Jev 1.14
$0.00004
Fits in one request
Qwen3.5 397B
$0.0024
Fits in one request

Jev 1.14 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Jev 1.14
$0.0021
Fits in one request
Qwen3.5 397B
$0.0408
Fits in one request

Jev 1.14 has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

Jev 1.14
$0.00924
Does not fit in one request
Cached input priced at the published list-input rate
Qwen3.5 397B
$0.168
Does not fit in one request
Cached input priced at the published list-input rate

Jev 1.14 does not fit this workload in one request. Qwen3.5 397B does not fit this workload in one request. Jev 1.14 has no published cached-input rate, so cached tokens use its listed input rate. Qwen3.5 397B has no published cached-input rate, so cached tokens use its listed input 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.

Jev 1.14

Not published

TypeSafe models and pricing

Qwen3.5 397B

Not published

Documented inputs

Jev 1.14

Not sourced

Qwen3.5 397B

Not sourced

Documented outputs

Jev 1.14

Not sourced

Qwen3.5 397B

Not sourced

Provider availability

Jev 1.14

Not sourced

Qwen3.5 397B

Not sourced

Reasoning profile

Jev 1.14

Unspecified

Qwen3.5 397B

Non-Reasoning

Weight access

Jev 1.14

Proprietary

Qwen3.5 397B

Open Weight

License

Jev 1.14

Proprietary

Qwen3.5 397B

Open Weight

Release date

Jev 1.14

2026-10-14

Qwen3.5 397B

2026-02-16

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
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
Workload cost
Repository review: $0.0021 vs $0.0408. Cache-heavy agent loop: $0.00924 vs $0.168.
Context tradeoff
Qwen3.5 397B has the larger documented window (128K).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Jev 1.14 or Qwen3.5 397B?

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Jev 1.14 or Qwen3.5 397B?

Jev 1.14 and Qwen3.5 397B are not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Jev 1.14 or Qwen3.5 397B?

Jev 1.14 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Jev 1.14 or Qwen3.5 397B?

For the stated presets, chat costs $0.00004 on Jev 1.14 and $0.0024 on Qwen3.5 397B; repository review costs $0.0021 and $0.0408; the cache-heavy agent loop costs $0.00924 and $0.168. Jev 1.14 does not fit this workload in one request. Qwen3.5 397B does not fit this workload in one request. Jev 1.14 has no published cached-input rate, so cached tokens use its listed input rate. Qwen3.5 397B has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Jev 1.14 or Qwen3.5 397B?

Qwen3.5 397B has the larger documented context window: 128K, compared with 64K.

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

    Jev 1.14—
    Qwen3.5 397B52.5%
    Source

    Not directly comparable

  • BrowseComp

    Jev 1.14—
    Qwen3.5 397B69%
    Source

    Not directly comparable

  • OSWorld-Verified

    Jev 1.14—
    Qwen3.5 397B62.2%
    Source

    Not directly comparable

  • Claw-Eval

    Jev 1.14—
    Qwen3.5 397B56.8%
    Source

    Not directly comparable

  • QwenClawBench

    Jev 1.14—
    Qwen3.5 397B51.8%
    Source

    Not directly comparable

  • τ³-bench results

    Jev 1.14—
    Qwen3.5 397B68.4%
    Source

    Not directly comparable

  • VITA-Bench

    Jev 1.14—
    Qwen3.5 397B43.7%
    Source

    Not directly comparable

  • DeepPlanning

    Jev 1.14—
    Qwen3.5 397B37.6%
    Source

    Not directly comparable

  • Toolathlon

    Jev 1.14—
    Qwen3.5 397B36.3%
    Source

    Not directly comparable

  • MCP Atlas

    Jev 1.14—
    Qwen3.5 397B46.1%
    Source

    Not directly comparable

  • MCP-Tasks

    Jev 1.14—
    Qwen3.5 397B74.2%
    Source

    Not directly comparable

  • WideResearch

    Jev 1.14—
    Qwen3.5 397B74.0%
    Source

    Not directly comparable

  • Gert Labs

    Jev 1.14—
    Qwen3.5 397B46.76%
    Source

    Not directly comparable

  • ResearchClawBench

    Jev 1.14—
    Qwen3.5 397B14.2%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Jev 1.14—
    Qwen3.5 397B76.2%
    Source

    Not directly comparable

  • LiveCodeBench v6

    Jev 1.14—
    Qwen3.5 397B83.6%
    Source

    Not directly comparable

  • SWE-bench Pro

    Jev 1.14—
    Qwen3.5 397B50.9%
    Source

    Not directly comparable

  • SWE Multilingual

    Jev 1.14—
    Qwen3.5 397B69.3%
    Source

    Not directly comparable

  • NL2Repo

    Jev 1.14—
    Qwen3.5 397B32.2%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Jev 1.14—
    Qwen3.5 397B52.5%
    Source

    Not directly comparable

Reasoning

  • LongBench v2

    Jev 1.14—
    Qwen3.5 397B63.2%
    Source

    Not directly comparable

  • AI-Needle

    Jev 1.14—
    Qwen3.5 397B68.7%
    Source

    Not directly comparable

Multimodal

  • MMMU

    Jev 1.14—
    Qwen3.5 397B85.0%
    Source

    Not directly comparable

  • MMMU-Pro

    Jev 1.14—
    Qwen3.5 397B79%
    Source

    Not directly comparable

  • RealWorldQA

    Jev 1.14—
    Qwen3.5 397B83.9%
    Source

    Not directly comparable

  • OmniDocBench 1.5

    Jev 1.14—
    Qwen3.5 397B90.8%
    Source

    Not directly comparable

  • Video-MME (with subtitle)

    Jev 1.14—
    Qwen3.5 397B87.5%
    Source

    Not directly comparable

  • Video-MME (w/o subtitle)

    Jev 1.14—
    Qwen3.5 397B83.7%
    Source

    Not directly comparable

  • MathVision

    Jev 1.14—
    Qwen3.5 397B88.6%
    Source

    Not directly comparable

  • We-Math

    Jev 1.14—
    Qwen3.5 397B87.9%
    Source

    Not directly comparable

  • DynaMath

    Jev 1.14—
    Qwen3.5 397B86.3%
    Source

    Not directly comparable

  • SimpleVQA

    Jev 1.14—
    Qwen3.5 397B67.1%
    Source

    Not directly comparable

  • CharXiv

    Jev 1.14—
    Qwen3.5 397B80.8%
    Source

    Not directly comparable

  • MMLongBench-Doc

    Jev 1.14—
    Qwen3.5 397B61.5%
    Source

    Not directly comparable

  • CC-OCR

    Jev 1.14—
    Qwen3.5 397B82.0%
    Source

    Not directly comparable

  • AI2D_TEST

    Jev 1.14—
    Qwen3.5 397B93.9%
    Source

    Not directly comparable

  • CountBench

    Jev 1.14—
    Qwen3.5 397B97.2%
    Source

    Not directly comparable

  • RefCOCO (avg)

    Jev 1.14—
    Qwen3.5 397B92.3%
    Source

    Not directly comparable

  • ODINW13

    Jev 1.14—
    Qwen3.5 397B47.0%
    Source

    Not directly comparable

  • ERQA

    Jev 1.14—
    Qwen3.5 397B67.5%
    Source

    Not directly comparable

  • VideoMMMU

    Jev 1.14—
    Qwen3.5 397B84.7%
    Source

    Not directly comparable

  • MLVU (M-Avg)

    Jev 1.14—
    Qwen3.5 397B86.7%
    Source

    Not directly comparable

  • ScreenSpot Pro

    Jev 1.14—
    Qwen3.5 397B65.6%
    Source

    Not directly comparable

  • V*

    Jev 1.14—
    Qwen3.5 397B95.8%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Jev 1.14—
    Qwen3.5 397B88.4%
    Source

    Not directly comparable

  • SuperGPQA

    Jev 1.14—
    Qwen3.5 397B70.4%
    Source

    Not directly comparable

  • MMLU-Pro

    Jev 1.14—
    Qwen3.5 397B87.8%
    Source

    Not directly comparable

  • MMLU-Redux

    Jev 1.14—
    Qwen3.5 397B94.9%
    Source

    Not directly comparable

  • C-Eval

    Jev 1.14—
    Qwen3.5 397B93%
    Source

    Not directly comparable

  • HLE

    Jev 1.14—
    Qwen3.5 397B28.7%
    Source

    Not directly comparable

Multilingual

  • MMLU-ProX

    Jev 1.14—
    Qwen3.5 397B84.7%
    Source

    Not directly comparable

  • NOVA-63

    Jev 1.14—
    Qwen3.5 397B59.1%
    Source

    Not directly comparable

  • INCLUDE

    Jev 1.14—
    Qwen3.5 397B85.6%
    Source

    Not directly comparable

  • PolyMath

    Jev 1.14—
    Qwen3.5 397B73.3%
    Source

    Not directly comparable

  • MAXIFE

    Jev 1.14—
    Qwen3.5 397B88.2%
    Source

    Not directly comparable

Instruction following

  • IFEval

    Jev 1.14—
    Qwen3.5 397B92.6%
    Source

    Not directly comparable

  • IFBench

    Jev 1.14—
    Qwen3.5 397B76.5%
    Source

    Not directly comparable

Math

  • AIME26

    Jev 1.14—
    Qwen3.5 397B93.3%
    Source

    Not directly comparable

  • HMMT Feb 2025

    Jev 1.14—
    Qwen3.5 397B94.8%
    Source

    Not directly comparable

  • HMMT Nov 2025

    Jev 1.14—
    Qwen3.5 397B92.7%
    Source

    Not directly comparable

  • HMMT Feb 2026

    Jev 1.14—
    Qwen3.5 397B87.9%
    Source

    Not directly comparable

  • MMAnswerBench

    Jev 1.14—
    Qwen3.5 397B80.9%
    Source

    Not directly comparable

62 public results · 0 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch Jev 1.14 vs Qwen3.5 397B

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

Read a sample issue

Join 5,600+ readers.

Last updated October 20, 2026