Skip to main content
BenchLM
Data

GPT-OSS 120B vs MiniMax M3

Updated October 14, 2026. Rank says MiniMax M3 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

MiniMax M3 has the higher public score estimate, 55 versus 37.36, 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
OpenAI logo
GPT-OSS 120B

OpenAI

37.36/100

Supported · Public rank #145

90% interval 23.6–51.1

Model B
MiniMax logo
MiniMax M3

MiniMax

55/100

Supported · Public rank #68

90% interval 45.6–64.4

Shared results
1
GPT-OSS 120B only
7
MiniMax M3 only
26
Like-for-like categories
1 / 8
Supported: GPT-OSS 120B and MiniMax M3How 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

    MiniMax M3

    MiniMax M3 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

    GPT-OSS 120B 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

    GPT-OSS 120B 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. GPT-OSS 120B does not fit this workload in one request. GPT-OSS 120B has no comparable published API token rate.

    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.

23.0GPT-OSS 120B36.5MiniMax M3

Directional only · BenchAlign v5.8

MiniMax M3 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.

Knowledge

Like-for-like
GPT-OSS 120B
38.6
Supported · #120/181
MiniMax M3
49.6
Supported · #80/181
Basis
BenchAlign v5.8 lane · 3 vs 2 public rows
Reading
MiniMax M3 leads · intervals overlap

Agentic

Directional only
GPT-OSS 120B
19.7
Estimated · #107/125
MiniMax M3
39.6
Supported · #66/125
Basis
BenchAlign v5.8 lane · 1 vs 9 public rows
Reading
Directional only

Coding

Directional only
GPT-OSS 120B
23.0
Estimated · #110/149
MiniMax M3
36.5
Supported · #73/149
Basis
BenchAlign v5.8 lane · 2 vs 10 public rows
Reading
Directional only

Instruction following

Directional only
GPT-OSS 120B
84.3
#48/144
MiniMax M3
93.8
#5/144
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Directional only

Reasoning

Not comparable
GPT-OSS 120B
61.6
Unranked · 2 rankable rows
MiniMax M3
82.9
#5/29
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
GPT-OSS 120B
Not ranked
MiniMax M3
61.5
#43/54
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Multilingual

Not comparable
GPT-OSS 120B
Not ranked
MiniMax M3
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
GPT-OSS 120B
Not ranked
MiniMax M3
Not ranked
Basis
Provisional lane · 0 vs 1 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

GPT-OSS 120B
Self-hosted; infrastructure cost varies
Fits in one request
MiniMax M3
$0.0009
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
MiniMax M3
$0.0186
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
MiniMax M3
$0.03
Fits in one request

GPT-OSS 120B does not fit this workload in one request. 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.

Context window

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

GPT-OSS 120B

128K

MiniMax M3

1M

API model ID

GPT-OSS 120B

Not sourced

MiniMax M3

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

MiniMax M3

$0.06 per 1M cached input tokens

Documented inputs

GPT-OSS 120B

Not sourced

MiniMax M3

Not sourced

Documented outputs

GPT-OSS 120B

Not sourced

MiniMax M3

Not sourced

Provider availability

GPT-OSS 120B

Not sourced

MiniMax M3

Not sourced

Reasoning profile

GPT-OSS 120B

Non-Reasoning

MiniMax M3

Non-Reasoning

Weight access

GPT-OSS 120B

Open Weight

MiniMax M3

Open Weight

License

GPT-OSS 120B

Open Weight

MiniMax M3

Open Weight

Release date

GPT-OSS 120B

2025-08-05

MiniMax M3

2026-06-01

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 M3 has the higher public score estimate, 55 versus 37.36, but the 90% score intervals overlap.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
MiniMax M3 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, GPT-OSS 120B or MiniMax M3?

MiniMax M3 has the higher public score estimate, 55 versus 37.36, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, GPT-OSS 120B or MiniMax M3?

MiniMax M3 scores higher for coding on the public lane, 36.5 to 23. GPT-OSS 120B 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, GPT-OSS 120B or MiniMax M3?

MiniMax M3 scores higher for agentic tasks on the public lane, 39.6 to 19.7. GPT-OSS 120B 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, GPT-OSS 120B or MiniMax M3?

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 MiniMax M3?

MiniMax M3 has the larger documented context window: 1M, 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 evidence34 rows

Agentic

  • Gert Labs

    GPT-OSS 120B29.61%
    Source
    MiniMax M3—

    Not directly comparable

  • Terminal-Bench 2.1

    GPT-OSS 120B—
    MiniMax M366.0%
    Source

    Not directly comparable

  • BrowseComp

    GPT-OSS 120B—
    MiniMax M383.5%
    Source

    Not directly comparable

  • OSWorld-Verified

    GPT-OSS 120B—
    MiniMax M370.1%
    Source

    Not directly comparable

  • MCP Atlas

    GPT-OSS 120B—
    MiniMax M374.2%
    Source

    Not directly comparable

  • Claw-Eval

    GPT-OSS 120B—
    MiniMax M374.5%
    Source

    Not directly comparable

  • BankerToolBench

    GPT-OSS 120B—
    MiniMax M376.1%
    Source

    Not directly comparable

  • ResearchClawBench

    GPT-OSS 120B—
    MiniMax M319.8%
    Source

    Not directly comparable

  • OSWorld 2.0

    GPT-OSS 120B—
    MiniMax M34.6%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    GPT-OSS 120B—
    MiniMax M353.6%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    GPT-OSS 120B62.4%
    Source
    MiniMax M380.5%
    Source

    MiniMax M3 leads this result

  • React Native Evals

    GPT-OSS 120B71.6%
    Source
    MiniMax M3—

    Not directly comparable

  • SWE-bench Pro

    GPT-OSS 120B—
    MiniMax M359%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    GPT-OSS 120B—
    MiniMax M366.0%
    Source

    Not directly comparable

  • NL2Repo

    GPT-OSS 120B—
    MiniMax M342.1%
    Source

    Not directly comparable

  • VIBE V2

    GPT-OSS 120B—
    MiniMax M350.1%
    Source

    Not directly comparable

  • SVG-Bench

    GPT-OSS 120B—
    MiniMax M363.7%
    Source

    Not directly comparable

  • KernelBench Hard

    GPT-OSS 120B—
    MiniMax M328.8%
    Source

    Not directly comparable

  • OpenHarmony Bench

    GPT-OSS 120B—
    MiniMax M348.4%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    GPT-OSS 120B—
    MiniMax M382.2%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    GPT-OSS 120B—
    MiniMax M375.0%
    Source

    Not directly comparable

Multimodal

  • OfficeQA Pro

    GPT-OSS 120B—
    MiniMax M345.1%
    Source

    Not directly comparable

  • OmniDocBench 1.5

    GPT-OSS 120B—
    MiniMax M391.6%
    Source

    Not directly comparable

  • MMMU-Pro

    GPT-OSS 120B—
    MiniMax M378.1%
    Source

    Not directly comparable

  • VideoMMMU

    GPT-OSS 120B—
    MiniMax M384.6%
    Source

    Not directly comparable

  • Video-MME (with subtitle)

    GPT-OSS 120B—
    MiniMax M385.4%
    Source

    Not directly comparable

Knowledge

  • MMLU

    GPT-OSS 120B90%
    Source
    MiniMax M3—

    Not directly comparable

  • GPQA

    GPT-OSS 120B80.1%
    Source
    MiniMax M3—

    Not directly comparable

  • HLE

    GPT-OSS 120B14.9%
    Source
    MiniMax M3—

    Not directly comparable

  • GPQA Diamond (Vals)

    GPT-OSS 120B—
    MiniMax M392.7%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    GPT-OSS 120B—
    MiniMax M384.2%
    Source

    Not directly comparable

Math

  • AIME 2024

    GPT-OSS 120B95.8%
    Source
    MiniMax M3—

    Not directly comparable

  • AIME 2025

    GPT-OSS 120B92.5%
    Source
    MiniMax M3—

    Not directly comparable

  • USAMO 2026

    GPT-OSS 120B—
    MiniMax M385.7%
    Source

    Not directly comparable

34 public results · 1 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch GPT-OSS 120B vs MiniMax M3

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

Read a sample issue

Join 5,500+ readers.

Last updated October 14, 2026