o1 vs Qwen3.5 397B

Updated September 29, 2026. We do not rank this pair: at least one has no public score. Public scores include evidence status and uncertainty.

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

OpenAI

37.48/100

Estimated · Public rank #131

90% interval 28.6–46.4

Model B

Qwen3.5 397B

Alibaba

—

Evidence status unavailable

90% interval unavailable

Shared results: 2
o1 only: 2
Qwen3.5 397B only: 36
Like-for-like categories: 0 / 8

Estimated: o1How 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
o1
o1 has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Qwen3.5 397B
Qwen3.5 397B 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
Qwen3.5 397B
Qwen3.5 397B 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
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
O1 and Qwen3.5 397B are 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. o1 does not fit this workload in one request. Qwen3.5 397B does not fit this workload in one request. o1 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.

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.

30.4o1—Qwen3.5 397B

Not comparable · BenchAlign v5.7

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.

GPQAKnowledge
Normalized gap 12.7
o1:75.7%
Qwen3.5 397B:88.4%
o1 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 v5.7 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

Directional only

o1: 84.5; #40/124
Qwen3.5 397B: 0.0; #124/124
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Directional only

Agentic

Not comparable

o1: Not ranked
Qwen3.5 397B: Not ranked
Basis: BenchAlign v5.7 lane · 0 vs 13 public rows
Reading: Not comparable

Coding

Not comparable

o1: 30.4; Estimated · #93/143
Qwen3.5 397B: Not ranked
Basis: BenchAlign v5.7 lane · 0 vs 3 public rows
Reading: Not comparable

Reasoning

Not comparable

o1: 67.0; Unranked · 2 rankable rows
Qwen3.5 397B: 61.0; Unranked · 2 rankable rows
Basis: Provisional lane · 0 vs 1 weighted rows
Reading: Not comparable

Multimodal

Not comparable

o1: Not ranked
Qwen3.5 397B: 63.9; #28/50
Basis: Provisional lane · 0 vs 2 weighted rows
Reading: Not comparable

Knowledge

Not comparable

o1: 40.7; Supported · #96/169
Qwen3.5 397B: Not ranked
Basis: BenchAlign v5.7 lane · 2 vs 6 public rows
Reading: Not comparable

Multilingual

Not comparable

o1: Not ranked
Qwen3.5 397B: 69.7; #5/12
Basis: Provisional lane · 0 vs 1 weighted rows
Reading: Not comparable

Math

Not comparable

o1: 32.5; Unranked · 1 rankable row
Qwen3.5 397B: 73.5; Unranked · 5 rankable rows
Basis: Provisional lane · 1 vs 2 weighted rows
Reading: Not comparable

Category scores with the server-provided evidence basis for o1 and Qwen3.5 397B
Category	o1	Qwen3.5 397B	Basis	Reading
Instruction following	84.5#40/124	0.0#124/124	Directional onlyProvisional lane · 0 vs 0 weighted rows	Directional only
Agentic	Not ranked	Not ranked	Not comparableBenchAlign v5.7 lane · 0 vs 13 public rows	Not comparable
Coding	30.4Estimated · #93/143	Not ranked	Not comparableBenchAlign v5.7 lane · 0 vs 3 public rows	Not comparable
Reasoning	67.0Unranked · 2 rankable rows	61.0Unranked · 2 rankable rows	Not comparableProvisional lane · 0 vs 1 weighted rows	Not comparable
Multimodal	Not ranked	63.9#28/50	Not comparableProvisional lane · 0 vs 2 weighted rows	Not comparable
Knowledge	40.7Supported · #96/169	Not ranked	Not comparableBenchAlign v5.7 lane · 2 vs 6 public rows	Not comparable
Multilingual	Not ranked	69.7#5/12	Not comparableProvisional lane · 0 vs 1 weighted rows	Not comparable
Math	32.5Unranked · 1 rankable row	73.5Unranked · 5 rankable rows	Not comparableProvisional lane · 1 vs 2 weighted rows	Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.7) 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

o1: $0.045; Fits in one request
Qwen3.5 397B: $0.0024; Fits in one request

Qwen3.5 397B has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

o1: $0.93; Fits in one request
Qwen3.5 397B: $0.0408; Fits in one request

Qwen3.5 397B has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

o1: $3.90; 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

o1 does not fit this workload in one request. Qwen3.5 397B does not fit this workload in one request. o1 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.

Specificationo1Qwen3.5 397B

Context window

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

200K

Qwen3.5 397B

128K

API model ID

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.

Not published

Qwen3.5 397B

Not published

Documented inputs

Not sourced

Qwen3.5 397B

Not sourced

Documented outputs

Not sourced

Qwen3.5 397B

Not sourced

Provider availability

Not sourced

Qwen3.5 397B

Not sourced

Reasoning profile

Reasoning

Qwen3.5 397B

Non-Reasoning

Weight access

Proprietary

Qwen3.5 397B

Open Weight

License

Proprietary

Qwen3.5 397B

Open Weight

Release date

2024-12-01

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: 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: Repository review: $0.93 vs $0.0408. Cache-heavy agent loop: $3.90 vs $0.168.
Context tradeoff: o1 has the larger documented window (200K).

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

Questions

Which is better, o1 or Qwen3.5 397B?

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, o1 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, o1 or Qwen3.5 397B?

O1 and Qwen3.5 397B are not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, o1 or Qwen3.5 397B?

For the stated presets, chat costs $0.045 on o1 and $0.0024 on Qwen3.5 397B; repository review costs $0.93 and $0.0408; the cache-heavy agent loop costs $3.90 and $0.168. o1 does not fit this workload in one request. Qwen3.5 397B does not fit this workload in one request. o1 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, o1 or Qwen3.5 397B?

o1 has the larger documented context window: 200K, compared with 128K.

Benchmark evidence

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

Browse raw public benchmark evidence40 rows

Agentic

Terminal-Bench 2.0
o1—
Qwen3.5 397B52.5%
Source
Not directly comparable
BrowseComp
o1—
Qwen3.5 397B62%
Source
Not directly comparable
Claw-Eval
o1—
Qwen3.5 397B56.8%
Source
Not directly comparable
QwenClawBench
o1—
Qwen3.5 397B51.8%
Source
Not directly comparable
τ³-bench results
o1—
Qwen3.5 397B68.4%
Source
Not directly comparable
VITA-Bench
o1—
Qwen3.5 397B43.7%
Source
Not directly comparable
DeepPlanning
o1—
Qwen3.5 397B37.6%
Source
Not directly comparable
Toolathlon
o1—
Qwen3.5 397B36.3%
Source
Not directly comparable
MCP Atlas
o1—
Qwen3.5 397B46.1%
Source
Not directly comparable
MCP-Tasks
o1—
Qwen3.5 397B74.2%
Source
Not directly comparable
WideResearch
o1—
Qwen3.5 397B74.0%
Source
Not directly comparable
Gert Labs
o1—
Qwen3.5 397B46.76%
Source
Not directly comparable
ResearchClawBench
o1—
Qwen3.5 397B14.2%
Source
Not directly comparable

Coding

SWE-bench Verified
o1—
Qwen3.5 397B76.2%
Source
Not directly comparable
LiveCodeBench v6
o1—
Qwen3.5 397B83.6%
Source
Not directly comparable
SWE-bench Pro
o1—
Qwen3.5 397B50.9%
Source
Not directly comparable

Reasoning

LongBench v2
o1—
Qwen3.5 397B63.2%
Source
Not directly comparable
AI-Needle
o1—
Qwen3.5 397B68.7%
Source
Not directly comparable

Multimodal

MMMU-Pro
o1—
Qwen3.5 397B79%
Source
Not directly comparable
MathVision
o1—
Qwen3.5 397B88.6%
Source
Not directly comparable
CharXiv
o1—
Qwen3.5 397B80.8%
Source
Not directly comparable
VideoMMMU
o1—
Qwen3.5 397B84.7%
Source
Not directly comparable
ScreenSpot Pro
o1—
Qwen3.5 397B65.6%
Source
Not directly comparable
V*
o1—
Qwen3.5 397B95.8%
Source
Not directly comparable

Knowledge

MMLU
o191.8%
Source
Qwen3.5 397B—
Not directly comparable
GPQA
o175.7%
Source
Qwen3.5 397B88.4%
Source
Qwen3.5 397B leads this result
SuperGPQA
o1—
Qwen3.5 397B70.4%
Source
Not directly comparable
MMLU-Pro
o1—
Qwen3.5 397B87.8%
Source
Not directly comparable
MMLU-Redux
o1—
Qwen3.5 397B94.9%
Source
Not directly comparable
C-Eval
o1—
Qwen3.5 397B93%
Source
Not directly comparable
HLE
o1—
Qwen3.5 397B28.7%
Source
Not directly comparable

Multilingual

MMLU-ProX
o1—
Qwen3.5 397B84.7%
Source
Not directly comparable
NOVA-63
o1—
Qwen3.5 397B59.1%
Source
Not directly comparable

Instruction following

IFEval
o192.2%
Source
Qwen3.5 397B92.6%
Source
Qwen3.5 397B leads this result

Math

FrontierMath v2 (Tiers 1-3)
o19.310%
Source
Qwen3.5 397B—
Not directly comparable
AIME26
o1—
Qwen3.5 397B93.3%
Source
Not directly comparable
HMMT Feb 2025
o1—
Qwen3.5 397B94.8%
Source
Not directly comparable
HMMT Nov 2025
o1—
Qwen3.5 397B92.7%
Source
Not directly comparable
HMMT Feb 2026
o1—
Qwen3.5 397B87.9%
Source
Not directly comparable
MMAnswerBench
o1—
Qwen3.5 397B80.9%
Source
Not directly comparable

40 public results · 2 shared

Related comparisons

Compare API pricing Read the methodology Open the model selector

Watch o1 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 2,000+ readers.

Last updated September 29, 2026

o1 vs Qwen3.5 397B

Decision reading

Which one for your work

Long documents

Chat turn cost

Repository review cost

Coding work

Agentic work

Cache-heavy agent loop cost

Which one for a specific job

What is actually comparable

Shape of the matched evidence

Category results, on a stated basis

Instruction following

Agentic

Coding

Reasoning

Multimodal

Knowledge

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, o1 or Qwen3.5 397B?

Which is better for coding, o1 or Qwen3.5 397B?

Which is better for agentic tasks, o1 or Qwen3.5 397B?

Which costs less, o1 or Qwen3.5 397B?

Which has the larger context window, o1 or Qwen3.5 397B?

Benchmark evidence

Agentic

Coding

Reasoning

Multimodal

Knowledge

Multilingual

Instruction following

Math

Related comparisons

Watch o1 vs Qwen3.5 397B