Skip to main content
BenchLM

GPT-5 mini vs MiniMax M2.7

Updated September 29, 2026. Rank says MiniMax M2.7 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

MiniMax M2.7 has the higher public score estimate, 47.85 versus 43.98, 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-5 mini

OpenAI

43.98/100

Supported · Public rank #107

90% interval 35.8–52.1

Model B
MiniMax logo
MiniMax M2.7

MiniMax

47.85/100

Supported · Public rank #89

90% interval 36.9–58.9

Shared results
1
GPT-5 mini only
0
MiniMax M2.7 only
22
Like-for-like categories
0 / 8
Supported: GPT-5 mini and MiniMax M2.7How 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 M2.7

    MiniMax M2.7 has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    MiniMax M2.7

    MiniMax M2.7 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

    GPT-5 mini

    GPT-5 mini 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

    GPT-5 mini 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-5 mini is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.

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

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

29.9GPT-5 mini36.0MiniMax M2.7

Directional only · BenchAlign v5.7

MiniMax M2.7 scores higher, but at least one score rests on Estimated evidence or a different benchmark set. Directional only, no winner.

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 v5.7 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.

Agentic

Directional only
GPT-5 mini
28.0
Estimated · #87/117
MiniMax M2.7
29.1
Supported · #82/117
Basis
BenchAlign v5.7 lane · 0 vs 7 public rows
Reading
Directional only

Coding

Directional only
GPT-5 mini
29.9
Estimated · #94/143
MiniMax M2.7
36.0
Supported · #77/143
Basis
BenchAlign v5.7 lane · 1 vs 11 public rows
Reading
Directional only

Reasoning

Not comparable
GPT-5 mini
Not ranked
MiniMax M2.7
76.1
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
GPT-5 mini
Not ranked
MiniMax M2.7
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Knowledge

Not comparable
GPT-5 mini
Not ranked
MiniMax M2.7
43.0
Supported · #86/169
Basis
BenchAlign v5.7 lane · 0 vs 4 public rows
Reading
Not comparable

Multilingual

Not comparable
GPT-5 mini
Not ranked
MiniMax M2.7
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
GPT-5 mini
Not ranked
MiniMax M2.7
91.6
#10/124
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
GPT-5 mini
Not ranked
MiniMax M2.7
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
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

GPT-5 mini
$0.00125
Fits in one request
MiniMax M2.7
$0.0009
Fits in one request

MiniMax M2.7 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

GPT-5 mini
$0.0185
Fits in one request
MiniMax M2.7
$0.0186
Fits in one request

GPT-5 mini 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-5 mini
$0.075
Does not fit in one request
Cached input priced at the published list-input rate
MiniMax M2.7
$0.078
Does not fit in one request
Cached input priced at the published list-input rate

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

Context window

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

GPT-5 mini

128K

MiniMax M2.7

200K

API model ID

GPT-5 mini

Not sourced

MiniMax M2.7

Not sourced

Cached-input rate

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

GPT-5 mini

Not published

MiniMax M2.7

Not published

Documented inputs

GPT-5 mini

Not sourced

MiniMax M2.7

Not sourced

Documented outputs

GPT-5 mini

Not sourced

MiniMax M2.7

Not sourced

Provider availability

GPT-5 mini

Not sourced

MiniMax M2.7

Not sourced

Reasoning profile

GPT-5 mini

Reasoning

MiniMax M2.7

Non-Reasoning

Weight access

GPT-5 mini

Proprietary

MiniMax M2.7

Open Weight

License

GPT-5 mini

Proprietary

MiniMax M2.7

Open Weight

Release date

GPT-5 mini

2025-08-07

MiniMax M2.7

2026-03-18

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, 47.85 versus 43.98, but the 90% score intervals overlap.
Workload cost
Repository review: $0.0185 vs $0.0186. Cache-heavy agent loop: $0.075 vs $0.078.
Context tradeoff
MiniMax M2.7 has the larger documented window (200K).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, GPT-5 mini or MiniMax M2.7?

MiniMax M2.7 has the higher public score estimate, 47.85 versus 43.98, 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-5 mini or MiniMax M2.7?

MiniMax M2.7 scores higher for coding on the public lane, 36 to 29.9. GPT-5 mini 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-5 mini or MiniMax M2.7?

MiniMax M2.7 scores higher for agentic tasks on the public lane, 29.1 to 28. GPT-5 mini 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-5 mini or MiniMax M2.7?

For the stated presets, chat costs $0.00125 on GPT-5 mini and $0.0009 on MiniMax M2.7; repository review costs $0.0185 and $0.0186; the cache-heavy agent loop costs $0.075 and $0.078. GPT-5 mini does not fit this workload in one request. MiniMax M2.7 does not fit this workload in one request. GPT-5 mini has no published cached-input rate, so cached tokens use its listed input rate. MiniMax M2.7 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, GPT-5 mini or MiniMax M2.7?

MiniMax M2.7 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 evidence23 rows

Agentic

  • Terminal-Bench 2.0

    GPT-5 mini—
    MiniMax M2.757%
    Source

    Not directly comparable

  • Toolathlon

    GPT-5 mini—
    MiniMax M2.746.3%
    Source

    Not directly comparable

  • MLE-Bench Lite

    GPT-5 mini—
    MiniMax M2.766.6%
    Source

    Not directly comparable

  • MM-ClawBench

    GPT-5 mini—
    MiniMax M2.762.7%
    Source

    Not directly comparable

  • Claw-Eval

    GPT-5 mini—
    MiniMax M2.748.7%
    Source

    Not directly comparable

  • Gert Labs

    GPT-5 mini—
    MiniMax M2.740.40%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    GPT-5 mini—
    MiniMax M2.748.7%
    Source

    Not directly comparable

Coding

  • Vibe Code Bench

    Shared source
    GPT-5 mini14.17%
    MiniMax M2.727.04%

    MiniMax M2.7 leads this result

  • SWE-bench Verified*

    GPT-5 mini—
    MiniMax M2.775.4%
    Source

    Not directly comparable

  • SWE-bench Pro

    GPT-5 mini—
    MiniMax M2.756.2%
    Source

    Not directly comparable

  • SWE-Rebench

    GPT-5 mini—
    MiniMax M2.751.9%
    Source

    Not directly comparable

  • SWE Multilingual

    GPT-5 mini—
    MiniMax M2.776.5%
    Source

    Not directly comparable

  • Multi-SWE Bench

    GPT-5 mini—
    MiniMax M2.752.7%
    Source

    Not directly comparable

  • VIBE-Pro

    GPT-5 mini—
    MiniMax M2.755.6%
    Source

    Not directly comparable

  • NL2Repo

    GPT-5 mini—
    MiniMax M2.739.8%
    Source

    Not directly comparable

  • React Native Evals

    GPT-5 mini—
    MiniMax M2.771.4%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    GPT-5 mini—
    MiniMax M2.779.9%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    GPT-5 mini—
    MiniMax M2.773.8%
    Source

    Not directly comparable

Knowledge

  • GPQA-D

    GPT-5 mini—
    MiniMax M2.787.0%
    Source

    Not directly comparable

  • MMLU-Pro (Arcee)

    GPT-5 mini—
    MiniMax M2.780.8%
    Source

    Not directly comparable

  • GPQA Diamond (Vals)

    GPT-5 mini—
    MiniMax M2.786.6%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    GPT-5 mini—
    MiniMax M2.780.4%
    Source

    Not directly comparable

Math

  • AIME25 (Arcee)

    GPT-5 mini—
    MiniMax M2.780.0%
    Source

    Not directly comparable

23 public results · 1 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch GPT-5 mini vs MiniMax M2.7

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