Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start the free Radar Brief
BenchLM
Google logo
Model A
Gemini 3.1 Pro

Google

56.25/100

Estimated · Public rank #98

90% interval 40.2–72.3

Gemini 3.1 Pro vs MiniMax M3

Updated August 30, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

MiniMax logo
Model B
MiniMax M3

MiniMax

68.73/100

Supported · Public rank #21

90% interval 63.5–74.0

Decision reading

MiniMax M3 has the higher public score estimate, 68.73 versus 56.25, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

3 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.

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.

  • Chat turn cost

    1K fresh input + 500 output tokens

    MiniMax M3

    MiniMax M3 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

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

    MiniMax M3

    MiniMax M3 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

    MiniMax M3

    MiniMax M3 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

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

Shared results
3
Gemini 3.1 Pro only
20
MiniMax M3 only
19
Like-for-like categories
0 / 8

1 category uses different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.

Multimodal

Directional only
Gemini 3.1 Pro
82.6
MiniMax M3
64.9
Weighted basis
2 vs 2 rows
Reading
Directional only

Agentic

Not comparable
Gemini 3.1 Pro
Not measured
MiniMax M3
72.3
Weighted basis
0 vs 3 rows
Reading
Not comparable

Coding

Not comparable
Gemini 3.1 Pro
Not measured
MiniMax M3
72.2
Weighted basis
0 vs 2 rows
Reading
Not comparable

Reasoning

Not comparable
Gemini 3.1 Pro
77.1
MiniMax M3
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
Gemini 3.1 Pro
Not measured
MiniMax M3
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Math

Not comparable
Gemini 3.1 Pro
31.8
MiniMax M3
85.7
Weighted basis
2 vs 1 rows
Reading
Not comparable

Multilingual

Not comparable
Gemini 3.1 Pro
Not measured
MiniMax M3
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Gemini 3.1 Pro
Not measured
MiniMax M3
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

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.

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

Gemini 3.1 Pro
$0.008
Fits in one request
MiniMax M3
$0.0009
Fits in one request

MiniMax M3 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Gemini 3.1 Pro
$0.136
Fits in one request
MiniMax M3
$0.0186
Fits in one request

MiniMax M3 has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

Gemini 3.1 Pro
$0.2
Fits in one request
MiniMax M3
$0.03
Fits in one request

MiniMax M3 has the lower modeled cost

Costs use the listed standard API rates.

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.

Gemini 3.1 Pro

$0.2 per 1M cached input tokens

Google Gemini API pricing

MiniMax M3

$0.06 per 1M cached input tokens

Reasoning profile

Gemini 3.1 Pro

Reasoning

MiniMax M3

Non-Reasoning

Weight access

Gemini 3.1 Pro

Proprietary

MiniMax M3

Open Weight

License

Gemini 3.1 Pro

Proprietary

MiniMax M3

Open Weight

Release date

Gemini 3.1 Pro

2026-02-19

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, 68.73 versus 56.25, but the 90% score intervals overlap.
Workload cost
Repository review: $0.136 vs $0.0186. Cache-heavy agent loop: $0.2 vs $0.03.
Context tradeoff
Both models list 1M.

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

Benchmark evidence

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

Browse raw public benchmark evidence42 rows

Agentic

  • Claw-Eval

    Gemini 3.1 Pro57.8%
    Source
    MiniMax M374.5%
    Source

    MiniMax M3 leads this result

  • DeepSearchQA

    Gemini 3.1 Pro69.7%
    Source
    MiniMax M3—

    Not directly comparable

  • τ²-bench results

    Gemini 3.1 Pro95.6%
    Source
    MiniMax M3—

    Not directly comparable

  • Gert Labs

    Gemini 3.1 Pro56.87%
    Source
    MiniMax M3—

    Not directly comparable

  • ResearchClawBench

    Shared source
    Gemini 3.1 Pro13.3%
    MiniMax M319.8%

    MiniMax M3 leads this result

  • Terminal-Bench 2.0

    Gemini 3.1 Pro—
    MiniMax M366%
    Source

    Not directly comparable

  • BrowseComp

    Gemini 3.1 Pro—
    MiniMax M383.5%
    Source

    Not directly comparable

  • OSWorld-Verified

    Gemini 3.1 Pro—
    MiniMax M370.1%
    Source

    Not directly comparable

  • MCP Atlas

    Gemini 3.1 Pro—
    MiniMax M374.2%
    Source

    Not directly comparable

  • BankerToolBench

    Gemini 3.1 Pro—
    MiniMax M376.1%
    Source

    Not directly comparable

  • OSWorld 2.0

    Gemini 3.1 Pro—
    MiniMax M34.6%
    Source

    Not directly comparable

Coding

  • LiveCodeBench Pro

    Gemini 3.1 Pro82.9%
    Source
    MiniMax M3—

    Not directly comparable

  • React Native Evals

    Gemini 3.1 Pro78.9%
    Source
    MiniMax M3—

    Not directly comparable

  • Vibe Code Bench

    Gemini 3.1 Pro32.03%
    Source
    MiniMax M3—

    Not directly comparable

  • SWE-bench Verified

    Gemini 3.1 Pro—
    MiniMax M380.5%
    Source

    Not directly comparable

  • SWE-bench Pro

    Gemini 3.1 Pro—
    MiniMax M359%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Gemini 3.1 Pro—
    MiniMax M366.0%
    Source

    Not directly comparable

  • NL2Repo

    Gemini 3.1 Pro—
    MiniMax M342.1%
    Source

    Not directly comparable

  • VIBE V2

    Gemini 3.1 Pro—
    MiniMax M350.1%
    Source

    Not directly comparable

  • SVG-Bench

    Gemini 3.1 Pro—
    MiniMax M363.7%
    Source

    Not directly comparable

  • KernelBench Hard

    Gemini 3.1 Pro—
    MiniMax M328.8%
    Source

    Not directly comparable

  • OpenHarmony Bench

    Gemini 3.1 Pro—
    MiniMax M348.4%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-2

    Gemini 3.1 Pro77.1%
    Source
    MiniMax M3—

    Not directly comparable

  • ARC-AGI-3

    Gemini 3.1 Pro0.4%
    Source
    MiniMax M3—

    Not directly comparable

Knowledge

  • GPQA-D

    Gemini 3.1 Pro94.3%
    Source
    MiniMax M3—

    Not directly comparable

  • HLE w/o tools

    Gemini 3.1 Pro45.4%
    Source
    MiniMax M3—

    Not directly comparable

  • HealthBench Hard

    Gemini 3.1 Pro20.6%
    Source
    MiniMax M3—

    Not directly comparable

  • MedXpertQA (Text)

    Gemini 3.1 Pro71.5%
    Source
    MiniMax M3—

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Gemini 3.1 Pro36.900%
    Source
    MiniMax M3—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Gemini 3.1 Pro16.700%
    Source
    MiniMax M3—

    Not directly comparable

  • USAMO 2026

    Gemini 3.1 Pro—
    MiniMax M385.7%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    Gemini 3.1 Pro83.9%
    Source
    MiniMax M378.1%
    Source

    Gemini 3.1 Pro leads this result

  • CharXiv

    Gemini 3.1 Pro80.2%
    Source
    MiniMax M3—

    Not directly comparable

  • ERQA

    Gemini 3.1 Pro69.4%
    Source
    MiniMax M3—

    Not directly comparable

  • SimpleVQA

    Gemini 3.1 Pro72.4%
    Source
    MiniMax M3—

    Not directly comparable

  • ScreenSpot Pro

    Gemini 3.1 Pro84.4%
    Source
    MiniMax M3—

    Not directly comparable

  • ZeroBench

    Gemini 3.1 Pro29.0%
    Source
    MiniMax M3—

    Not directly comparable

  • MedXpertQA (MM)

    Gemini 3.1 Pro81.3%
    Source
    MiniMax M3—

    Not directly comparable

  • OfficeQA Pro

    Gemini 3.1 Pro—
    MiniMax M345.1%
    Source

    Not directly comparable

  • OmniDocBench 1.5

    Gemini 3.1 Pro—
    MiniMax M391.6%
    Source

    Not directly comparable

  • VideoMMMU

    Gemini 3.1 Pro—
    MiniMax M384.6%
    Source

    Not directly comparable

  • Video-MME (with subtitle)

    Gemini 3.1 Pro—
    MiniMax M385.4%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Gemini 3.1 Pro or MiniMax M3?

MiniMax M3 has the higher public score estimate, 68.73 versus 56.25, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Gemini 3.1 Pro or MiniMax M3?

The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.

Which is better for agentic tasks, Gemini 3.1 Pro or MiniMax M3?

The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.

Which costs less, Gemini 3.1 Pro or MiniMax M3?

For the stated presets, chat costs $0.008 on Gemini 3.1 Pro and $0.0009 on MiniMax M3; repository review costs $0.136 and $0.0186; the cache-heavy agent loop costs $0.2 and $0.03. Costs use the listed standard API rates.

Which has the larger context window, Gemini 3.1 Pro or MiniMax M3?

Both models list the same context window, 1M.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 30, 2026

Watch Gemini 3.1 Pro 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.