Skip to main content
BenchLM

GPT-6 Luna vs MiniMax M3

Updated September 23, 2026. Rank says GPT-6 Luna is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInSocial cardCSVJSON

Decision reading

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead. 0 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-6 Luna

OpenAI

66.52/100

Estimated · Public rank #21

90% interval 55.0–78.0

Model B
MiniMax logo
MiniMax M3

MiniMax

55.28/100

Supported · Public rank #60

90% interval 46.6–63.9

Shared results
0
GPT-6 Luna only
7
MiniMax M3 only
27
Like-for-like categories
1 / 8
Estimated: GPT-6 Luna · Supported: 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.

  • Coding work

    Code generation, repair, and software-engineering tasks

    GPT-6 Luna

    GPT-6 Luna leads on the public coding lane, 53.9 to 39.6, with Supported evidence for both models, although the 90% intervals overlap.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    GPT-6 Luna

    GPT-6 Luna has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    GPT-6 Luna

    GPT-6 Luna 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

  • Cache-heavy agent loop cost

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

    GPT-6 Luna

    GPT-6 Luna has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Repository review cost

    50K fresh input + 3K output tokens

    GPT-6 Luna

    GPT-6 Luna has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    GPT-6 Luna is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.

    Confidence: limited

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.

53.9GPT-6 Luna39.6MiniMax M3

Like-for-like · BenchAlign v5.6

GPT-6 Luna leads the like-for-like coding row, although the 90% intervals overlap.

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.

2 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.

A shared-evidence shape is not available.

BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.6 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
GPT-6 Luna
53.9
Supported · #32/135
MiniMax M3
39.6
Supported · #63/135
Basis
BenchAlign v5.6 lane · 1 vs 10 public rows
Reading
GPT-6 Luna leads · intervals overlap

Agentic

Directional only
GPT-6 Luna
55.4
Estimated · #26/105
MiniMax M3
39.8
Supported · #45/105
Basis
BenchAlign v5.6 lane · 1 vs 9 public rows
Reading
Directional only

Knowledge

Directional only
GPT-6 Luna
66.3
Estimated · #18/160
MiniMax M3
48.0
Supported · #62/160
Basis
BenchAlign v5.6 lane · 5 vs 2 public rows
Reading
Directional only

Reasoning

Not comparable
GPT-6 Luna
78.3
#6/18
MiniMax M3
78.0
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
GPT-6 Luna
71.3
Unranked · 1 rankable row
MiniMax M3
52.0
#36/50
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Multilingual

Not comparable
GPT-6 Luna
Not ranked
MiniMax M3
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
GPT-6 Luna
Not ranked
MiniMax M3
92.4
#5/124
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
GPT-6 Luna
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 v5.6) 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-6 Luna
$0.00035
Fits in one request
MiniMax M3
$0.0009
Fits in one request

GPT-6 Luna has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

GPT-6 Luna
$0.0065
Fits in one request
MiniMax M3
$0.0186
Fits in one request

GPT-6 Luna has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

GPT-6 Luna
$0.009
Fits in one request
MiniMax M3
$0.03
Fits in one request

GPT-6 Luna has the lower modeled cost

Costs use the listed standard API rates.

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.

Cached-input rate

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

GPT-6 Luna

$0.01 per 1M cached input tokens

OpenAI GPT-6 Luna model documentation

MiniMax M3

$0.06 per 1M cached input tokens

Provider availability

GPT-6 Luna

Generally Available · OpenAI Responses API, OpenAI Chat Completions API, ChatGPT Work, Codex

OpenAI GPT-6 Sol and Luna launch

MiniMax M3

Not sourced

Reasoning profile

GPT-6 Luna

Reasoning

MiniMax M3

Non-Reasoning

Weight access

GPT-6 Luna

Proprietary

MiniMax M3

Open Weight

License

GPT-6 Luna

Proprietary

MiniMax M3

Open Weight

Release date

GPT-6 Luna

2026-09-16

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
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
Workload cost
Repository review: $0.0065 vs $0.0186. Cache-heavy agent loop: $0.009 vs $0.03.
Context tradeoff
GPT-6 Luna has the larger documented window (1.05M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, GPT-6 Luna or MiniMax M3?

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, GPT-6 Luna or MiniMax M3?

GPT-6 Luna leads the public coding lane, 53.9 to 39.6, with Supported evidence for both models, although the 90% intervals overlap.

Which is better for agentic tasks, GPT-6 Luna or MiniMax M3?

GPT-6 Luna scores higher for agentic tasks on the public lane, 55.4 to 39.8. GPT-6 Luna 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-6 Luna or MiniMax M3?

For the stated presets, chat costs $0.00035 on GPT-6 Luna and $0.0009 on MiniMax M3; repository review costs $0.0065 and $0.0186; the cache-heavy agent loop costs $0.009 and $0.03. Costs use the listed standard API rates.

Which has the larger context window, GPT-6 Luna or MiniMax M3?

GPT-6 Luna has the larger documented context window: 1.05M, compared with 1M.

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

  • ExploitGym

    GPT-6 Luna11.6%
    Source
    MiniMax M3—

    Not directly comparable

  • Terminal-Bench 2.1

    GPT-6 Luna—
    MiniMax M366.0%
    Source

    Not directly comparable

  • BrowseComp

    GPT-6 Luna—
    MiniMax M383.5%
    Source

    Not directly comparable

  • OSWorld-Verified

    GPT-6 Luna—
    MiniMax M370.1%
    Source

    Not directly comparable

  • MCP Atlas

    GPT-6 Luna—
    MiniMax M374.2%
    Source

    Not directly comparable

  • Claw-Eval

    GPT-6 Luna—
    MiniMax M374.5%
    Source

    Not directly comparable

  • BankerToolBench

    GPT-6 Luna—
    MiniMax M376.1%
    Source

    Not directly comparable

  • ResearchClawBench

    GPT-6 Luna—
    MiniMax M319.8%
    Source

    Not directly comparable

  • OSWorld 2.0

    GPT-6 Luna—
    MiniMax M34.6%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    GPT-6 Luna—
    MiniMax M353.6%
    Source

    Not directly comparable

Coding

  • DeepSWE

    GPT-6 Luna66.6%
    Source
    MiniMax M3—

    Not directly comparable

  • SWE-bench Verified

    GPT-6 Luna—
    MiniMax M380.5%
    Source

    Not directly comparable

  • SWE-bench Pro

    GPT-6 Luna—
    MiniMax M359%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    GPT-6 Luna—
    MiniMax M366.0%
    Source

    Not directly comparable

  • NL2Repo

    GPT-6 Luna—
    MiniMax M342.1%
    Source

    Not directly comparable

  • VIBE V2

    GPT-6 Luna—
    MiniMax M350.1%
    Source

    Not directly comparable

  • SVG-Bench

    GPT-6 Luna—
    MiniMax M363.7%
    Source

    Not directly comparable

  • KernelBench Hard

    GPT-6 Luna—
    MiniMax M328.8%
    Source

    Not directly comparable

  • OpenHarmony Bench

    GPT-6 Luna—
    MiniMax M348.4%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    GPT-6 Luna—
    MiniMax M382.2%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    GPT-6 Luna—
    MiniMax M375.0%
    Source

    Not directly comparable

Multimodal

  • OfficeQA Pro

    GPT-6 Luna—
    MiniMax M345.1%
    Source

    Not directly comparable

  • OmniDocBench 1.5

    GPT-6 Luna—
    MiniMax M391.6%
    Source

    Not directly comparable

  • MMMU-Pro

    GPT-6 Luna—
    MiniMax M378.1%
    Source

    Not directly comparable

  • VideoMMMU

    GPT-6 Luna—
    MiniMax M384.6%
    Source

    Not directly comparable

  • Video-MME (with subtitle)

    GPT-6 Luna—
    MiniMax M385.4%
    Source

    Not directly comparable

Knowledge

  • HealthBench (raw)

    GPT-6 Luna50.0%
    Source
    MiniMax M3—

    Not directly comparable

  • HealthBench (length-adjusted)

    GPT-6 Luna54.5%
    Source
    MiniMax M3—

    Not directly comparable

  • HealthBench Professional

    GPT-6 Luna60.8%
    Source
    MiniMax M3—

    Not directly comparable

  • HealthBench Professional (raw)

    GPT-6 Luna61.2%
    Source
    MiniMax M3—

    Not directly comparable

  • HealthBench Hard

    GPT-6 Luna31.4%
    Source
    MiniMax M3—

    Not directly comparable

  • GPQA Diamond (Vals)

    GPT-6 Luna—
    MiniMax M392.7%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    GPT-6 Luna—
    MiniMax M384.2%
    Source

    Not directly comparable

Math

  • USAMO 2026

    GPT-6 Luna—
    MiniMax M385.7%
    Source

    Not directly comparable

34 public results · 0 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch GPT-6 Luna vs MiniMax M3

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 23, 2026