MiniMax M2.7 vs Qwen3.5-122B-A10B

Updated September 27, 2026. Rank says MiniMax M2.7 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Decision reading

MiniMax M2.7 has the higher public score estimate, 48.08 versus 40.06, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A

MiniMax M2.7

MiniMax

48.08/100

Supported · Public rank #83

90% interval 37.2–58.9

Model B

Qwen3.5-122B-A10B

Alibaba

40.06/100

Estimated · Public rank #113

90% interval 19.5–60.6

Shared results: 1
MiniMax M2.7 only: 22
Qwen3.5-122B-A10B only: 14
Like-for-like categories: 2 / 8

Supported: MiniMax M2.7 · Estimated: Qwen3.5-122B-A10BHow 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
Qwen3.5-122B-A10B
Qwen3.5-122B-A10B has the larger documented context window.
Confidence: documented

Show secondary and unsupported calls

Coding work
Code generation, repair, and software-engineering tasks
No clear pick
The like-for-like coding result is a practical tie on the public lane (within 0.5 points).
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Qwen3.5-122B-A10B 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
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. MiniMax M2.7 does not fit this workload in one request. MiniMax M2.7 has no published cached-input rate, so cached tokens use its listed input rate. Qwen3.5-122B-A10B 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.

36.1MiniMax M2.735.7Qwen3.5-122B-A10B

Like-for-like · BenchAlign v5.7

The like-for-like coding row is a practical tie.

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.

Terminal-Bench 2.0Agentic
Normalized gap 7.6
MiniMax M2.7:57%
Qwen3.5-122B-A10B:49.4%
MiniMax M2.7 source Qwen3.5-122B-A10B 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.

Coding

Like-for-like

MiniMax M2.7: 36.1; Supported · #70/135
Qwen3.5-122B-A10B: 35.7; Supported · #73/135
Basis: BenchAlign v5.7 lane · 11 vs 1 public rows
Reading: Practical tie

Knowledge

Like-for-like

MiniMax M2.7: 43.0; Supported · #79/158
Qwen3.5-122B-A10B: 41.5; Supported · #86/158
Basis: BenchAlign v5.7 lane · 4 vs 3 public rows
Reading: MiniMax M2.7 leads · intervals overlap

Agentic

Directional only

MiniMax M2.7: 25.2; Supported · #79/105
Qwen3.5-122B-A10B: 23.1; Estimated · #84/105
Basis: BenchAlign v5.7 lane · 7 vs 3 public rows
Reading: Directional only

Instruction following

Directional only

MiniMax M2.7: 91.6; #10/124
Qwen3.5-122B-A10B: 91.6; #11/124
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Directional only

Reasoning

Not comparable

MiniMax M2.7: 75.9; Unranked · 2 rankable rows
Qwen3.5-122B-A10B: 49.8; Unranked · 3 rankable rows
Basis: Provisional lane · 0 vs 1 weighted rows
Reading: Not comparable

Multimodal

Not comparable

MiniMax M2.7: Not ranked
Qwen3.5-122B-A10B: 57.0; #34/50
Basis: Provisional lane · 0 vs 1 weighted rows
Reading: Not comparable

Multilingual

Not comparable

MiniMax M2.7: Not ranked
Qwen3.5-122B-A10B: 36.8; #10/12
Basis: Provisional lane · 0 vs 1 weighted rows
Reading: Not comparable

Math

Not comparable

MiniMax M2.7: Not ranked
Qwen3.5-122B-A10B: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Category scores with the server-provided evidence basis for MiniMax M2.7 and Qwen3.5-122B-A10B
Category	MiniMax M2.7	Qwen3.5-122B-A10B	Basis	Reading
Coding	36.1Supported · #70/135	35.7Supported · #73/135	Like-for-likeBenchAlign v5.7 lane · 11 vs 1 public rows	Practical tie
Knowledge	43.0Supported · #79/158	41.5Supported · #86/158	Like-for-likeBenchAlign v5.7 lane · 4 vs 3 public rows	MiniMax M2.7 leads · intervals overlap
Agentic	25.2Supported · #79/105	23.1Estimated · #84/105	Directional onlyBenchAlign v5.7 lane · 7 vs 3 public rows	Directional only
Instruction following	91.6#10/124	91.6#11/124	Directional onlyProvisional lane · 0 vs 0 weighted rows	Directional only
Reasoning	75.9Unranked · 2 rankable rows	49.8Unranked · 3 rankable rows	Not comparableProvisional lane · 0 vs 1 weighted rows	Not comparable
Multimodal	Not ranked	57.0#34/50	Not comparableProvisional lane · 0 vs 1 weighted rows	Not comparable
Multilingual	Not ranked	36.8#10/12	Not comparableProvisional lane · 0 vs 1 weighted rows	Not comparable
Math	Not ranked	Not ranked	Not comparableProvisional lane · 0 vs 0 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

MiniMax M2.7: $0.0009; Fits in one request
Qwen3.5-122B-A10B: Self-hosted; infrastructure cost varies; Fits in one request

Qwen3.5-122B-A10B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

MiniMax M2.7: $0.0186; Fits in one request
Qwen3.5-122B-A10B: Self-hosted; infrastructure cost varies; Fits in one request

Qwen3.5-122B-A10B has no comparable published API token rate.

Cache-heavy agent loop

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

MiniMax M2.7: $0.078; Does not fit in one request; Cached input priced at the published list-input rate
Qwen3.5-122B-A10B: Self-hosted; infrastructure cost varies; Fits in one request; Cached-input rate unavailable

MiniMax M2.7 does not fit this workload in one request. MiniMax M2.7 has no published cached-input rate, so cached tokens use its listed input rate. Qwen3.5-122B-A10B 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.

SpecificationMiniMax M2.7Qwen3.5-122B-A10B

Context window

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

MiniMax M2.7

200K

Qwen3.5-122B-A10B

262K

API model ID

MiniMax M2.7

Not sourced

Qwen3.5-122B-A10B

Not sourced

Cached-input rate

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

MiniMax M2.7

Not published

Qwen3.5-122B-A10B

No comparable hosted API rate

Documented inputs

MiniMax M2.7

Not sourced

Qwen3.5-122B-A10B

Not sourced

Documented outputs

MiniMax M2.7

Not sourced

Qwen3.5-122B-A10B

Not sourced

Provider availability

MiniMax M2.7

Not sourced

Qwen3.5-122B-A10B

Not sourced

Reasoning profile

MiniMax M2.7

Non-Reasoning

Qwen3.5-122B-A10B

Reasoning

Weight access

MiniMax M2.7

Open Weight

Qwen3.5-122B-A10B

Open Weight

License

MiniMax M2.7

Open Weight

Qwen3.5-122B-A10B

Open Weight

Release date

MiniMax M2.7

2026-03-18

Qwen3.5-122B-A10B

2026-03-04

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: MiniMax M2.7 has the higher public score estimate, 48.08 versus 40.06, but the 90% score intervals overlap.
Workload cost: A complete comparable API-rate estimate is not available for both models.
Context tradeoff: Qwen3.5-122B-A10B has the larger documented window (262K).

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

Questions

Which is better, MiniMax M2.7 or Qwen3.5-122B-A10B?

MiniMax M2.7 has the higher public score estimate, 48.08 versus 40.06, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, MiniMax M2.7 or Qwen3.5-122B-A10B?

The like-for-like coding row is a practical tie on the public lane, 36.1 against 35.7, inside the 0.5-point band BenchLM treats as level.

Which is better for agentic tasks, MiniMax M2.7 or Qwen3.5-122B-A10B?

MiniMax M2.7 scores higher for agentic tasks on the public lane, 25.2 to 23.1. Qwen3.5-122B-A10B 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, MiniMax M2.7 or Qwen3.5-122B-A10B?

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, MiniMax M2.7 or Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B has the larger documented context window: 262K, compared with 200K.

Benchmark evidence

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

Browse raw public benchmark evidence37 rows

Agentic

Terminal-Bench 2.0
MiniMax M2.757%
Source
Qwen3.5-122B-A10B49.4%
Source
MiniMax M2.7 leads this result
Toolathlon
MiniMax M2.746.3%
Source
Qwen3.5-122B-A10B—
Not directly comparable
MLE-Bench Lite
MiniMax M2.766.6%
Source
Qwen3.5-122B-A10B—
Not directly comparable
MM-ClawBench
MiniMax M2.762.7%
Source
Qwen3.5-122B-A10B—
Not directly comparable
Claw-Eval
MiniMax M2.748.7%
Source
Qwen3.5-122B-A10B—
Not directly comparable
Gert Labs
MiniMax M2.740.40%
Source
Qwen3.5-122B-A10B—
Not directly comparable
Terminal-Bench 2.1 (Vals)
MiniMax M2.748.7%
Source
Qwen3.5-122B-A10B—
Not directly comparable
BrowseComp
MiniMax M2.7—
Qwen3.5-122B-A10B63.8%
Source
Not directly comparable
OSWorld-Verified
MiniMax M2.7—
Qwen3.5-122B-A10B58%
Source
Not directly comparable

Coding

SWE-bench Verified*
MiniMax M2.775.4%
Source
Qwen3.5-122B-A10B—
Not directly comparable
SWE-bench Pro
MiniMax M2.756.2%
Source
Qwen3.5-122B-A10B—
Not directly comparable
SWE-Rebench
MiniMax M2.751.9%
Source
Qwen3.5-122B-A10B—
Not directly comparable
SWE Multilingual
MiniMax M2.776.5%
Source
Qwen3.5-122B-A10B—
Not directly comparable
Multi-SWE Bench
MiniMax M2.752.7%
Source
Qwen3.5-122B-A10B—
Not directly comparable
VIBE-Pro
MiniMax M2.755.6%
Source
Qwen3.5-122B-A10B—
Not directly comparable
NL2Repo
MiniMax M2.739.8%
Source
Qwen3.5-122B-A10B—
Not directly comparable
Vibe Code Bench
MiniMax M2.727.04%
Source
Qwen3.5-122B-A10B—
Not directly comparable
React Native Evals
MiniMax M2.771.4%
Source
Qwen3.5-122B-A10B—
Not directly comparable
LiveCodeBench (Vals)
MiniMax M2.779.9%
Source
Qwen3.5-122B-A10B—
Not directly comparable
SWE-bench (Vals)
MiniMax M2.773.8%
Source
Qwen3.5-122B-A10B—
Not directly comparable
SWE-bench Verified
MiniMax M2.7—
Qwen3.5-122B-A10B72%
Source
Not directly comparable

Reasoning

LongBench v2
MiniMax M2.7—
Qwen3.5-122B-A10B60.2%
Source
Not directly comparable

Multimodal

MMMU
MiniMax M2.7—
Qwen3.5-122B-A10B83.9%
Source
Not directly comparable
MMVU
MiniMax M2.7—
Qwen3.5-122B-A10B74.7%
Source
Not directly comparable
MathVision
MiniMax M2.7—
Qwen3.5-122B-A10B86.2%
Source
Not directly comparable
CharXiv
MiniMax M2.7—
Qwen3.5-122B-A10B77.2%
Source
Not directly comparable
V*
MiniMax M2.7—
Qwen3.5-122B-A10B93.2%
Source
Not directly comparable

Knowledge

GPQA-D
MiniMax M2.787.0%
Source
Qwen3.5-122B-A10B—
Not directly comparable
MMLU-Pro (Arcee)
MiniMax M2.780.8%
Source
Qwen3.5-122B-A10B—
Not directly comparable
GPQA Diamond (Vals)
MiniMax M2.786.6%
Source
Qwen3.5-122B-A10B—
Not directly comparable
MMLU-Pro (Vals)
MiniMax M2.780.4%
Source
Qwen3.5-122B-A10B—
Not directly comparable
MMLU-Pro
MiniMax M2.7—
Qwen3.5-122B-A10B86.7%
Source
Not directly comparable
SuperGPQA
MiniMax M2.7—
Qwen3.5-122B-A10B67.1%
Source
Not directly comparable
GPQA
MiniMax M2.7—
Qwen3.5-122B-A10B86.6%
Source
Not directly comparable

Multilingual

MMLU-ProX
MiniMax M2.7—
Qwen3.5-122B-A10B82.2%
Source
Not directly comparable

Instruction following

IFEval
MiniMax M2.7—
Qwen3.5-122B-A10B93.4%
Source
Not directly comparable

Math

AIME25 (Arcee)
MiniMax M2.780.0%
Source
Qwen3.5-122B-A10B—
Not directly comparable

37 public results · 1 shared

Related comparisons

Compare API pricing Read the methodology Open the model selector

Watch MiniMax M2.7 vs Qwen3.5-122B-A10B

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 27, 2026

MiniMax M2.7 vs Qwen3.5-122B-A10B

Decision reading

Which one for your work

Long documents

Coding work

Agentic work

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

Coding

Knowledge

Agentic

Instruction following

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, MiniMax M2.7 or Qwen3.5-122B-A10B?

Which is better for coding, MiniMax M2.7 or Qwen3.5-122B-A10B?

Which is better for agentic tasks, MiniMax M2.7 or Qwen3.5-122B-A10B?

Which costs less, MiniMax M2.7 or Qwen3.5-122B-A10B?

Which has the larger context window, MiniMax M2.7 or Qwen3.5-122B-A10B?

Benchmark evidence

Agentic

Coding

Reasoning

Multimodal

Knowledge

Multilingual

Instruction following

Math

Related comparisons

Watch MiniMax M2.7 vs Qwen3.5-122B-A10B