GPT-OSS 120B vs Qwen3.5 397B

Updated October 17, 2026. Rank says Qwen3.5 397B is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Decision reading

Qwen3.5 397B has the higher public point estimate, 55.34 versus 37.32. Their conditional score ranges overlap. These ranges do not establish rank confidence. 4 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A

GPT-OSS 120B

OpenAI

37.32/100

Supported · Public rank #148

90% interval 23.6–51.1

Model B

Qwen3.5 397B

Alibaba

55.34/100

Estimated · Public rank #65

Conditional range 41.0–69.7

Shared results: 4
GPT-OSS 120B only: 4
Qwen3.5 397B only: 58
Like-for-like categories: 0 / 8

Supported: GPT-OSS 120B · 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.

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
Qwen3.5 397B 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
GPT-OSS 120B and Qwen3.5 397B are scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
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
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. GPT-OSS 120B does not fit this workload in one request. Qwen3.5 397B does not fit this workload in one request. Qwen3.5 397B has no published cached-input rate, so cached tokens use its listed input rate. GPT-OSS 120B has no comparable published API token rate.
Confidence: rate-fallback
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.

Pick the job you would use them for

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

23.0GPT-OSS 120B—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 leaderboard Shortlist models for this job

Same basis rules as the category table below

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.

SWE-bench VerifiedCoding
Normalized gap 13.8
GPT-OSS 120B:62.4%
Qwen3.5 397B:76.2%
GPT-OSS 120B source Qwen3.5 397B source
HLEKnowledge
Normalized gap 13.8
GPT-OSS 120B:14.9%
Qwen3.5 397B:28.7%
GPT-OSS 120B source Qwen3.5 397B source
GPQAKnowledge
Normalized gap 8.3
GPT-OSS 120B:80.1%
Qwen3.5 397B:88.4%
GPT-OSS 120B source Qwen3.5 397B source

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

GPT-OSS 120B: 19.5; Estimated · #110/128
Qwen3.5 397B: 43.8; Estimated · #61/128
Basis: BenchAlign v5.8 lane · 1 vs 14 public rows
Reading: Directional only

Knowledge

Directional only

GPT-OSS 120B: 38.6; Supported · #122/184
Qwen3.5 397B: 53.1; Estimated · #68/184
Basis: BenchAlign v5.8 lane · 3 vs 6 public rows
Reading: Directional only

Instruction following

Directional only

GPT-OSS 120B: 84.3; #50/148
Qwen3.5 397B: 79.9; #59/148
Basis: Provisional lane · 0 vs 1 weighted rows
Reading: Directional only

Coding

Not comparable

GPT-OSS 120B: 23.0; Estimated · #111/150
Qwen3.5 397B: Not ranked
Basis: BenchAlign v5.8 lane · 2 vs 6 public rows
Reading: Not comparable

Reasoning

Not comparable

GPT-OSS 120B: 61.6; Unranked · 2 rankable rows
Qwen3.5 397B: 74.9; Unranked · 2 rankable rows
Basis: Provisional lane · 0 vs 1 weighted rows
Reading: Not comparable

Multimodal

Not comparable

GPT-OSS 120B: Not ranked
Qwen3.5 397B: 73.6; #29/54
Basis: Provisional lane · 0 vs 2 weighted rows
Reading: Not comparable

Multilingual

Not comparable

GPT-OSS 120B: Not ranked
Qwen3.5 397B: 93.8; #5/17
Basis: Provisional lane · 0 vs 1 weighted rows
Reading: Not comparable

Math

Not comparable

GPT-OSS 120B: Not ranked
Qwen3.5 397B: 81.7; Unranked · 5 rankable rows
Basis: Provisional lane · 0 vs 2 weighted rows
Reading: Not comparable

Category scores with the server-provided evidence basis for GPT-OSS 120B and Qwen3.5 397B
Category	GPT-OSS 120B	Qwen3.5 397B	Basis	Reading
Agentic	19.5Estimated · #110/128	43.8Estimated · #61/128	Directional onlyBenchAlign v5.8 lane · 1 vs 14 public rows	Directional only
Knowledge	38.6Supported · #122/184	53.1Estimated · #68/184	Directional onlyBenchAlign v5.8 lane · 3 vs 6 public rows	Directional only
Instruction following	84.3#50/148	79.9#59/148	Directional onlyProvisional lane · 0 vs 1 weighted rows	Directional only
Coding	23.0Estimated · #111/150	Not ranked	Not comparableBenchAlign v5.8 lane · 2 vs 6 public rows	Not comparable
Reasoning	61.6Unranked · 2 rankable rows	74.9Unranked · 2 rankable rows	Not comparableProvisional lane · 0 vs 1 weighted rows	Not comparable
Multimodal	Not ranked	73.6#29/54	Not comparableProvisional lane · 0 vs 2 weighted rows	Not comparable
Multilingual	Not ranked	93.8#5/17	Not comparableProvisional lane · 0 vs 1 weighted rows	Not comparable
Math	Not ranked	81.7Unranked · 5 rankable rows	Not comparableProvisional lane · 0 vs 2 weighted rows	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

GPT-OSS 120B: Self-hosted; infrastructure cost varies; Fits in one request
Qwen3.5 397B: $0.0024; Fits in one request

GPT-OSS 120B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

GPT-OSS 120B: Self-hosted; infrastructure cost varies; Fits in one request
Qwen3.5 397B: $0.0408; Fits in one request

GPT-OSS 120B has no comparable published API token rate.

Cache-heavy agent loop

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

GPT-OSS 120B: Self-hosted; infrastructure cost varies; Does not fit in one request; Cached-input rate unavailable
Qwen3.5 397B: $0.168; Does not fit in one request; Cached input priced at the published list-input rate

GPT-OSS 120B does not fit this workload in one request. Qwen3.5 397B does not fit this workload in one request. Qwen3.5 397B has no published cached-input rate, so cached tokens use its listed input rate. GPT-OSS 120B 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.

SpecificationGPT-OSS 120BQwen3.5 397B

Context window

Maximum documented context; output-token limits may be lower.

GPT-OSS 120B

128K

Qwen3.5 397B

128K

API model ID

GPT-OSS 120B

Not sourced

Qwen3.5 397B

Not sourced

Cached-input rate

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

GPT-OSS 120B

No comparable hosted API rate

Qwen3.5 397B

Not published

Documented inputs

GPT-OSS 120B

Not sourced

Qwen3.5 397B

Not sourced

Documented outputs

GPT-OSS 120B

Not sourced

Qwen3.5 397B

Not sourced

Provider availability

GPT-OSS 120B

Not sourced

Qwen3.5 397B

Not sourced

Reasoning profile

GPT-OSS 120B

Non-Reasoning

Qwen3.5 397B

Non-Reasoning

Weight access

GPT-OSS 120B

Open Weight

Qwen3.5 397B

Open Weight

License

GPT-OSS 120B

Open Weight

Qwen3.5 397B

Open Weight

Release date

GPT-OSS 120B

2025-08-05

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: Qwen3.5 397B has the higher public point estimate, 55.34 versus 37.32. 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: Both models list 128K.

Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, GPT-OSS 120B or Qwen3.5 397B?

Qwen3.5 397B has the higher public point estimate, 55.34 versus 37.32. 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, GPT-OSS 120B or Qwen3.5 397B?

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

Which is better for agentic tasks, GPT-OSS 120B or Qwen3.5 397B?

Qwen3.5 397B scores higher for agentic tasks on the public lane, 43.8 to 19.5. GPT-OSS 120B and Qwen3.5 397B are 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, GPT-OSS 120B or Qwen3.5 397B?

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, GPT-OSS 120B or Qwen3.5 397B?

Both models list the same context window, 128K.

Self-host vs API cost

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

GPT-OSS 120B

API / mo$0

Self-host / mo$3,495

Break-even—

Qwen3.5 397B

API / mo$3,150

Self-host / moNot listed

Break-even—

Proprietary model — self-hosting not applicable.

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 evidence66 rows

Agentic

Gert Labs
Shared source
GPT-OSS 120B29.61%
Qwen3.5 397B46.76%
Qwen3.5 397B leads this result
Terminal-Bench 2.0
GPT-OSS 120B—
Qwen3.5 397B52.5%
Source
Not directly comparable
BrowseComp
GPT-OSS 120B—
Qwen3.5 397B69%
Source
Not directly comparable
OSWorld-Verified
GPT-OSS 120B—
Qwen3.5 397B62.2%
Source
Not directly comparable
Claw-Eval
GPT-OSS 120B—
Qwen3.5 397B56.8%
Source
Not directly comparable
QwenClawBench
GPT-OSS 120B—
Qwen3.5 397B51.8%
Source
Not directly comparable
τ³-bench results
GPT-OSS 120B—
Qwen3.5 397B68.4%
Source
Not directly comparable
VITA-Bench
GPT-OSS 120B—
Qwen3.5 397B43.7%
Source
Not directly comparable
DeepPlanning
GPT-OSS 120B—
Qwen3.5 397B37.6%
Source
Not directly comparable
Toolathlon
GPT-OSS 120B—
Qwen3.5 397B36.3%
Source
Not directly comparable
MCP Atlas
GPT-OSS 120B—
Qwen3.5 397B46.1%
Source
Not directly comparable
MCP-Tasks
GPT-OSS 120B—
Qwen3.5 397B74.2%
Source
Not directly comparable
WideResearch
GPT-OSS 120B—
Qwen3.5 397B74.0%
Source
Not directly comparable
ResearchClawBench
GPT-OSS 120B—
Qwen3.5 397B14.2%
Source
Not directly comparable

Coding

SWE-bench Verified
GPT-OSS 120B62.4%
Source
Qwen3.5 397B76.2%
Source
Qwen3.5 397B leads this result
React Native Evals
GPT-OSS 120B71.6%
Source
Qwen3.5 397B—
Not directly comparable
LiveCodeBench v6
GPT-OSS 120B—
Qwen3.5 397B83.6%
Source
Not directly comparable
SWE-bench Pro
GPT-OSS 120B—
Qwen3.5 397B50.9%
Source
Not directly comparable
SWE Multilingual
GPT-OSS 120B—
Qwen3.5 397B69.3%
Source
Not directly comparable
NL2Repo
GPT-OSS 120B—
Qwen3.5 397B32.2%
Source
Not directly comparable
Terminal-Bench 2.0
GPT-OSS 120B—
Qwen3.5 397B52.5%
Source
Not directly comparable

Reasoning

LongBench v2
GPT-OSS 120B—
Qwen3.5 397B63.2%
Source
Not directly comparable
AI-Needle
GPT-OSS 120B—
Qwen3.5 397B68.7%
Source
Not directly comparable

Multimodal

MMMU
GPT-OSS 120B—
Qwen3.5 397B85.0%
Source
Not directly comparable
MMMU-Pro
GPT-OSS 120B—
Qwen3.5 397B79%
Source
Not directly comparable
RealWorldQA
GPT-OSS 120B—
Qwen3.5 397B83.9%
Source
Not directly comparable
OmniDocBench 1.5
GPT-OSS 120B—
Qwen3.5 397B90.8%
Source
Not directly comparable
Video-MME (with subtitle)
GPT-OSS 120B—
Qwen3.5 397B87.5%
Source
Not directly comparable
Video-MME (w/o subtitle)
GPT-OSS 120B—
Qwen3.5 397B83.7%
Source
Not directly comparable
MathVision
GPT-OSS 120B—
Qwen3.5 397B88.6%
Source
Not directly comparable
We-Math
GPT-OSS 120B—
Qwen3.5 397B87.9%
Source
Not directly comparable
DynaMath
GPT-OSS 120B—
Qwen3.5 397B86.3%
Source
Not directly comparable
SimpleVQA
GPT-OSS 120B—
Qwen3.5 397B67.1%
Source
Not directly comparable
CharXiv
GPT-OSS 120B—
Qwen3.5 397B80.8%
Source
Not directly comparable
MMLongBench-Doc
GPT-OSS 120B—
Qwen3.5 397B61.5%
Source
Not directly comparable
CC-OCR
GPT-OSS 120B—
Qwen3.5 397B82.0%
Source
Not directly comparable
AI2D_TEST
GPT-OSS 120B—
Qwen3.5 397B93.9%
Source
Not directly comparable
CountBench
GPT-OSS 120B—
Qwen3.5 397B97.2%
Source
Not directly comparable
RefCOCO (avg)
GPT-OSS 120B—
Qwen3.5 397B92.3%
Source
Not directly comparable
ODINW13
GPT-OSS 120B—
Qwen3.5 397B47.0%
Source
Not directly comparable
ERQA
GPT-OSS 120B—
Qwen3.5 397B67.5%
Source
Not directly comparable
VideoMMMU
GPT-OSS 120B—
Qwen3.5 397B84.7%
Source
Not directly comparable
MLVU (M-Avg)
GPT-OSS 120B—
Qwen3.5 397B86.7%
Source
Not directly comparable
ScreenSpot Pro
GPT-OSS 120B—
Qwen3.5 397B65.6%
Source
Not directly comparable
V*
GPT-OSS 120B—
Qwen3.5 397B95.8%
Source
Not directly comparable

Knowledge

MMLU
GPT-OSS 120B90%
Source
Qwen3.5 397B—
Not directly comparable
GPQA
GPT-OSS 120B80.1%
Source
Qwen3.5 397B88.4%
Source
Qwen3.5 397B leads this result
HLE
GPT-OSS 120B14.9%
Source
Qwen3.5 397B28.7%
Source
Qwen3.5 397B leads this result
SuperGPQA
GPT-OSS 120B—
Qwen3.5 397B70.4%
Source
Not directly comparable
MMLU-Pro
GPT-OSS 120B—
Qwen3.5 397B87.8%
Source
Not directly comparable
MMLU-Redux
GPT-OSS 120B—
Qwen3.5 397B94.9%
Source
Not directly comparable
C-Eval
GPT-OSS 120B—
Qwen3.5 397B93%
Source
Not directly comparable

Multilingual

MMLU-ProX
GPT-OSS 120B—
Qwen3.5 397B84.7%
Source
Not directly comparable
NOVA-63
GPT-OSS 120B—
Qwen3.5 397B59.1%
Source
Not directly comparable
INCLUDE
GPT-OSS 120B—
Qwen3.5 397B85.6%
Source
Not directly comparable
PolyMath
GPT-OSS 120B—
Qwen3.5 397B73.3%
Source
Not directly comparable
MAXIFE
GPT-OSS 120B—
Qwen3.5 397B88.2%
Source
Not directly comparable

Instruction following

IFEval
GPT-OSS 120B—
Qwen3.5 397B92.6%
Source
Not directly comparable
IFBench
GPT-OSS 120B—
Qwen3.5 397B76.5%
Source
Not directly comparable

Math

AIME 2024
GPT-OSS 120B95.8%
Source
Qwen3.5 397B—
Not directly comparable
AIME 2025
GPT-OSS 120B92.5%
Source
Qwen3.5 397B—
Not directly comparable
AIME26
GPT-OSS 120B—
Qwen3.5 397B93.3%
Source
Not directly comparable
HMMT Feb 2025
GPT-OSS 120B—
Qwen3.5 397B94.8%
Source
Not directly comparable
HMMT Nov 2025
GPT-OSS 120B—
Qwen3.5 397B92.7%
Source
Not directly comparable
HMMT Feb 2026
GPT-OSS 120B—
Qwen3.5 397B87.9%
Source
Not directly comparable
MMAnswerBench
GPT-OSS 120B—
Qwen3.5 397B80.9%
Source
Not directly comparable

66 public results · 4 shared

Related comparisons

Compare API pricing Read the methodology Open the model selector

Watch GPT-OSS 120B 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 17, 2026

GPT-OSS 120B vs Qwen3.5 397B

Decision reading

Which one for your work

Coding work

Agentic work

Long documents

Chat turn cost

Cache-heavy agent loop cost

Repository review cost

Which one for a specific job

What is actually comparable

Shape of the matched evidence

Category results, on a stated basis

Agentic

Knowledge

Instruction following

Coding

Reasoning

Multimodal

Multilingual

Math

What each workload costs

Chat turn

Repository review

Cache-heavy agent loop

Specification differences

Context window

API model ID

Cached-input rate

Documented inputs

Documented outputs

Provider availability

Reasoning profile

Weight access

License

Release date

If you already use one of these models

Questions

Which is better, GPT-OSS 120B or Qwen3.5 397B?

Which is better for coding, GPT-OSS 120B or Qwen3.5 397B?

Which is better for agentic tasks, GPT-OSS 120B or Qwen3.5 397B?

Which costs less, GPT-OSS 120B or Qwen3.5 397B?

Which has the larger context window, GPT-OSS 120B or Qwen3.5 397B?

Self-host vs API cost

Benchmark evidence

Agentic

Coding

Reasoning

Multimodal

Knowledge

Multilingual

Instruction following

Math

Related comparisons

Watch GPT-OSS 120B vs Qwen3.5 397B