Skip to main content
BenchLM
Data

Ornith-1.5-35B-A3B vs Qwen3.8 Max

Updated October 2, 2026. Rank says Qwen3.8 Max is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInSocial cardCSVAPI/MCP

Decision reading

Qwen3.8 Max has the higher public point estimate, 72.12 versus 32.61. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. 12 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Ornith-1.5-35B-A3B

Ornith AI

32.61/100

Estimated · Public rank #152

Conditional range 18.3–47.0

Model B
Alibaba logo
Qwen3.8 Max

Alibaba

72.12/100

Supported · Public rank #16

90% interval 69.1–75.1

Shared results
12
Ornith-1.5-35B-A3B only
6
Qwen3.8 Max only
48
Like-for-like categories
0 / 8
Estimated: Ornith-1.5-35B-A3B · Supported: Qwen3.8 Max. 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

    Qwen3.8 Max

    Qwen3.8 Max 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

    Ornith-1.5-35B-A3B 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

    Ornith-1.5-35B-A3B 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.

24.0Ornith-1.5-35B-A3B55.4Qwen3.8 Max

Directional only · BenchAlign v5.8

Qwen3.8 Max 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.

3 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.

Agentic

Directional only
Ornith-1.5-35B-A3B
23.5
Estimated · #95/119
Qwen3.8 Max
65.2
Supported · #14/119
Basis
BenchAlign v5.8 lane · 7 vs 15 public rows
Reading
Directional only

Coding

Directional only
Ornith-1.5-35B-A3B
24.0
Estimated · #110/144
Qwen3.8 Max
55.4
Supported · #30/144
Basis
BenchAlign v5.8 lane · 7 vs 12 public rows
Reading
Directional only

Knowledge

Directional only
Ornith-1.5-35B-A3B
34.5
Estimated · #119/171
Qwen3.8 Max
66.1
Supported · #23/171
Basis
BenchAlign v5.8 lane · 4 vs 6 public rows
Reading
Directional only

Reasoning

Not comparable
Ornith-1.5-35B-A3B
Not ranked
Qwen3.8 Max
87.7
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Ornith-1.5-35B-A3B
Not ranked
Qwen3.8 Max
88.4
#5/49
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Ornith-1.5-35B-A3B
Not ranked
Qwen3.8 Max
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Ornith-1.5-35B-A3B
Not ranked
Qwen3.8 Max
89.8
#16/125
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Math

Not comparable
Ornith-1.5-35B-A3B
Not ranked
Qwen3.8 Max
Not ranked
Basis
Provisional lane · 0 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

Ornith-1.5-35B-A3B
Self-hosted; infrastructure cost varies
Fits in one request
Qwen3.8 Max
API rate not published
Fits in one request

Ornith-1.5-35B-A3B has no comparable published API token rate. Qwen3.8 Max has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Ornith-1.5-35B-A3B
Self-hosted; infrastructure cost varies
Fits in one request
Qwen3.8 Max
API rate not published
Fits in one request

Ornith-1.5-35B-A3B has no comparable published API token rate. Qwen3.8 Max has no comparable published API token rate.

Cache-heavy agent loop

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

Ornith-1.5-35B-A3B
Self-hosted; infrastructure cost varies
Fits in one request
Cached-input rate unavailable
Qwen3.8 Max
API rate not published
Fits in one request
Cached-input rate unavailable

Ornith-1.5-35B-A3B has no comparable published API token rate. 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.

Documented inputs

Ornith-1.5-35B-A3B

Not sourced

Qwen3.8 Max

Not sourced

Documented outputs

Ornith-1.5-35B-A3B

Not sourced

Qwen3.8 Max

Not sourced

Provider availability

Ornith-1.5-35B-A3B

Not sourced

Qwen3.8 Max

Not sourced

Reasoning profile

Ornith-1.5-35B-A3B

Reasoning

Qwen3.8 Max

Reasoning

Weight access

Ornith-1.5-35B-A3B

Open Weight

Qwen3.8 Max

Open Weight

License

Ornith-1.5-35B-A3B

Open Weight

Qwen3.8 Max

Open Weight

Release date

Ornith-1.5-35B-A3B

2026-08-18

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
Qwen3.8 Max has the higher public point estimate, 72.12 versus 32.61. 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
Qwen3.8 Max has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Ornith-1.5-35B-A3B or Qwen3.8 Max?

Qwen3.8 Max has the higher public point estimate, 72.12 versus 32.61. 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, Ornith-1.5-35B-A3B or Qwen3.8 Max?

Qwen3.8 Max scores higher for coding on the public lane, 55.4 to 24. Ornith-1.5-35B-A3B 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, Ornith-1.5-35B-A3B or Qwen3.8 Max?

Qwen3.8 Max scores higher for agentic tasks on the public lane, 65.2 to 23.5. Ornith-1.5-35B-A3B 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, Ornith-1.5-35B-A3B 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, Ornith-1.5-35B-A3B or Qwen3.8 Max?

Qwen3.8 Max 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 evidence66 rows

Agentic

  • Terminal-Bench 2.1

    Ornith-1.5-35B-A3B67.8%
    Source
    Qwen3.8 Max86.6%
    Source

    Qwen3.8 Max leads this result

  • HLE w/ tools

    Ornith-1.5-35B-A3B33.4%
    Source
    Qwen3.8 Max56.2%
    Source

    Qwen3.8 Max leads this result

  • MCP Atlas

    Ornith-1.5-35B-A3B70.2%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Toolathlon-Verified

    Ornith-1.5-35B-A3B48.7%
    Source
    Qwen3.8 Max72.5%
    Source

    Qwen3.8 Max leads this result

  • WideResearch

    Ornith-1.5-35B-A3B67.8%
    Source
    Qwen3.8 Max81.9%
    Source

    Qwen3.8 Max leads this result

  • BrowseComp

    Ornith-1.5-35B-A3B67.6%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Claw-Eval

    Ornith-1.5-35B-A3B72.5%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • CoWorkBench

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max74.8%
    Source

    Not directly comparable

  • JobBench

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max53.4%
    Source

    Not directly comparable

  • skillsBench

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max70.2%
    Source

    Not directly comparable

  • Agents' Last Exam

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max52.4%
    Source

    Not directly comparable

  • AutomationBench

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max27.3%
    Source

    Not directly comparable

  • OSWorld-Verified

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max86.1%
    Source

    Not directly comparable

  • OSWorld 2.0

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max19.4%
    Source

    Not directly comparable

  • WebArena-Verified

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max66.8%
    Source

    Not directly comparable

  • AndroidWorld

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max85.3%
    Source

    Not directly comparable

  • MobileWorld

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max77.8%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max67.4%
    Source

    Not directly comparable

Coding

  • Terminal-Bench 2.1

    Ornith-1.5-35B-A3B67.8%
    Source
    Qwen3.8 Max86.6%
    Source

    Qwen3.8 Max leads this result

  • SWE-bench Verified

    Ornith-1.5-35B-A3B79%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • SWE-bench Pro

    Ornith-1.5-35B-A3B59.6%
    Source
    Qwen3.8 Max67.7%
    Source

    Qwen3.8 Max leads this result

  • SWE Multilingual

    Ornith-1.5-35B-A3B71.4%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • DeepSWE

    Ornith-1.5-35B-A3B22.0%
    Source
    Qwen3.8 Max56.6%
    Source

    Qwen3.8 Max leads this result

  • frontierBench

    Ornith-1.5-35B-A3B5.1%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • NL2Repo

    Ornith-1.5-35B-A3B46.2%
    Source
    Qwen3.8 Max55.9%
    Source

    Qwen3.8 Max leads this result

  • FrontierSWE

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max73.5%
    Source

    Not directly comparable

  • MLS-Bench Lite

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max41.0%
    Source

    Not directly comparable

  • PaperBench

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max93.0%
    Source

    Not directly comparable

  • VulcanBench v3

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max81.2%
    Source

    Not directly comparable

  • OpenHarmony Bench

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max60.8%
    Source

    Not directly comparable

  • FrontierSWE v2

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max15.8%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max87.9%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max85.6%
    Source

    Not directly comparable

Reasoning

  • MRCRv2

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max92.9%
    Source

    Not directly comparable

  • LongBench v2

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max66.3%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max82.3%
    Source

    Not directly comparable

  • MathVision

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max95.2%
    Source

    Not directly comparable

  • MathVision w/ Python

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max97.7%
    Source

    Not directly comparable

  • BabyVision

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max82.0%
    Source

    Not directly comparable

  • BabyVision w/ Python

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max91.3%
    Source

    Not directly comparable

  • ZeroBench

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max24.0%
    Source

    Not directly comparable

  • ZeroBench w/ Python

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max49.0%
    Source

    Not directly comparable

  • MedXpertQA (MM)

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max80.4%
    Source

    Not directly comparable

  • ScreenSpot Pro

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max84.5%
    Source

    Not directly comparable

  • Vision2Web

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max69.0%
    Source

    Not directly comparable

  • CharXiv w/o tools

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max88.4%
    Source

    Not directly comparable

  • CharXiv

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max93.5%
    Source

    Not directly comparable

  • OmniDocBench 1.5

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max92.1%
    Source

    Not directly comparable

  • OCRBench V2

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max74.2%
    Source

    Not directly comparable

  • CC-OCR

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max79.6%
    Source

    Not directly comparable

  • RealWorldQA

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max88.0%
    Source

    Not directly comparable

  • ERQA

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max77.8%
    Source

    Not directly comparable

  • SimpleVQA

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max75.0%
    Source

    Not directly comparable

  • PerceptionBench

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max63.5%
    Source

    Not directly comparable

  • Video-MME (with subtitle)

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max90.4%
    Source

    Not directly comparable

  • VideoMMMU

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max88.7%
    Source

    Not directly comparable

  • MMVU

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max82.4%
    Source

    Not directly comparable

  • MLVU (M-Avg)

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max90.8%
    Source

    Not directly comparable

  • LVBench

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max81.8%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Ornith-1.5-35B-A3B89.2%
    Source
    Qwen3.8 Max92.6%
    Source

    Qwen3.8 Max leads this result

  • GPQA-D

    Ornith-1.5-35B-A3B89.2%
    Source
    Qwen3.8 Max92.6%
    Source

    Qwen3.8 Max leads this result

  • HLE

    Ornith-1.5-35B-A3B25.6%
    Source
    Qwen3.8 Max43.6%
    Source

    Qwen3.8 Max leads this result

  • HLE w/o tools

    Ornith-1.5-35B-A3B25.6%
    Source
    Qwen3.8 Max43.6%
    Source

    Qwen3.8 Max leads this result

  • GPQA Diamond (Vals)

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max93.7%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max88.6%
    Source

    Not directly comparable

Instruction following

  • IFBench

    Ornith-1.5-35B-A3B—
    Qwen3.8 Max82.8%
    Source

    Not directly comparable

66 public results · 12 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch Ornith-1.5-35B-A3B 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 2,000+ readers.

Last updated October 2, 2026