Skip to main content
BenchLM
Data

Mistral Large 4 vs Step 5 Preview

Updated October 6, 2026. Rank says Step 5 Preview is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInSocial cardCSVAPI/MCP

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
Mistral logo
Mistral Large 4

Mistral

53.69/100

Estimated · Public rank #69

Conditional range 39.3–68.0

Model B
StepFun logo
Step 5 Preview

StepFun

70.26/100

Estimated · Public rank #17

Conditional range 60.5–80.0

Shared results
0
Mistral Large 4 only
3
Step 5 Preview only
22
Like-for-like categories
1 / 8
Estimated: Mistral Large 4 and Step 5 Preview. Conditional ranges do not establish rank confidence.How 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.

  • Chat turn cost

    1K fresh input + 500 output tokens

    Mistral Large 4

    Mistral Large 4 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

    Mistral Large 4

    Mistral Large 4 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

    Mistral Large 4

    Mistral Large 4 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

    Mistral Large 4 is not ranked on the public lane for coding, so no winner is named for coding.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    Mistral Large 4 is not ranked on the public lane for agentic, so no winner is named for agentic.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

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.

—Mistral Large 461.4Step 5 Preview

Not comparable · BenchAlign v5.8

The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.

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.

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 v5.8 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
Mistral Large 4
55.1
Supported · #51/173
Step 5 Preview
67.1
Supported · #19/173
Basis
BenchAlign v5.8 lane · 0 vs 2 public rows
Reading
Step 5 Preview leads · intervals overlap

Agentic

Not comparable
Mistral Large 4
Not ranked
Step 5 Preview
63.5
Estimated · #17/120
Basis
BenchAlign v5.8 lane · 2 vs 11 public rows
Reading
Not comparable

Coding

Not comparable
Mistral Large 4
Not ranked
Step 5 Preview
61.4
Estimated · #17/144
Basis
BenchAlign v5.8 lane · 1 vs 6 public rows
Reading
Not comparable

Reasoning

Not comparable
Mistral Large 4
78.2
Unranked · 2 rankable rows
Step 5 Preview
79.6
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Mistral Large 4
73.6
Unranked · 1 rankable row
Step 5 Preview
61.2
#28/49
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Mistral Large 4
Not ranked
Step 5 Preview
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Mistral Large 4
Not ranked
Step 5 Preview
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Mistral Large 4
Not ranked
Step 5 Preview
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 v5.8) 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

Mistral Large 4
$0.00172
Fits in one request
Step 5 Preview
$0.00235
Fits in one request

Mistral Large 4 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Mistral Large 4
$0.04027
Fits in one request
Step 5 Preview
$0.0581
Fits in one request

Mistral Large 4 has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

Mistral Large 4
$0.0485
Fits in one request
Step 5 Preview
$0.057
Fits in one request

Mistral Large 4 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.

Reasoning profile

Mistral Large 4

Hybrid

Step 5 Preview

Reasoning

Weight access

Mistral Large 4

Pending

Step 5 Preview

Pending

License

Mistral Large 4

Pending

Step 5 Preview

Pending

Release date

Mistral Large 4

2026-10-06

Step 5 Preview

2026-09-20

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: $0.04027 vs $0.0581. Cache-heavy agent loop: $0.0485 vs $0.057.
Context tradeoff
Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Mistral Large 4 or Step 5 Preview?

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, Mistral Large 4 or Step 5 Preview?

Mistral Large 4 is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Mistral Large 4 or Step 5 Preview?

Mistral Large 4 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Mistral Large 4 or Step 5 Preview?

For the stated presets, chat costs $0.00172 on Mistral Large 4 and $0.00235 on Step 5 Preview; repository review costs $0.04027 and $0.0581; the cache-heavy agent loop costs $0.0485 and $0.057. Costs use the listed standard API rates.

Which has the larger context window, Mistral Large 4 or Step 5 Preview?

Both models list the same context window, 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 evidence25 rows

Agentic

  • Cybench

    Mistral Large 493.0%
    Source
    Step 5 Preview—

    Not directly comparable

  • Finance Agent v2

    Mistral Large 454.7%
    Source
    Step 5 Preview—

    Not directly comparable

  • Terminal-Bench 2.1

    Mistral Large 4—
    Step 5 Preview85.0%
    Source

    Not directly comparable

  • Terminal-Bench 4.0

    Mistral Large 4—
    Step 5 Preview33.30%
    Source

    Not directly comparable

  • CyberGym

    Mistral Large 4—
    Step 5 Preview84.7%
    Source

    Not directly comparable

  • AutomationBench

    Mistral Large 4—
    Step 5 Preview44.0%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Mistral Large 4—
    Step 5 Preview74.1%
    Source

    Not directly comparable

  • MCP Atlas

    Mistral Large 4—
    Step 5 Preview85.6%
    Source

    Not directly comparable

  • JobBench

    Mistral Large 4—
    Step 5 Preview59.0%
    Source

    Not directly comparable

  • APEX-Agents

    Mistral Large 4—
    Step 5 Preview37.8%
    Source

    Not directly comparable

  • DRACO

    Mistral Large 4—
    Step 5 Preview83.3%
    Source

    Not directly comparable

  • BrowseComp

    Mistral Large 4—
    Step 5 Preview88.7%
    Source

    Not directly comparable

  • Agents' Last Exam

    Mistral Large 4—
    Step 5 Preview29.5%
    Source

    Not directly comparable

Coding

  • Vibe Code Bench

    Mistral Large 478.40%
    Source
    Step 5 Preview—

    Not directly comparable

  • DeepSWE

    Mistral Large 4—
    Step 5 Preview67.7%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Mistral Large 4—
    Step 5 Preview85.0%
    Source

    Not directly comparable

  • SciCode

    Mistral Large 4—
    Step 5 Preview58.9%
    Source

    Not directly comparable

  • ProgramBench

    Mistral Large 4—
    Step 5 Preview80.5%
    Source

    Not directly comparable

  • sweMarathon

    Mistral Large 4—
    Step 5 Preview72.7%
    Source

    Not directly comparable

  • MLS-Bench Lite

    Mistral Large 4—
    Step 5 Preview40.5%
    Source

    Not directly comparable

Reasoning

  • CritPt

    Mistral Large 4—
    Step 5 Preview20.9%
    Source

    Not directly comparable

Multimodal

  • OfficeQA Pro

    Mistral Large 4—
    Step 5 Preview60.3%
    Source

    Not directly comparable

  • MMMU-Pro

    Mistral Large 4—
    Step 5 Preview76%
    Source

    Not directly comparable

Knowledge

  • GPQA-D

    Mistral Large 4—
    Step 5 Preview93.5%
    Source

    Not directly comparable

  • HLE

    Mistral Large 4—
    Step 5 Preview46.5%
    Source

    Not directly comparable

25 public results · 0 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch Mistral Large 4 vs Step 5 Preview

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 6, 2026