Skip to main content
BenchLM
Data

Mistral Large 4 vs Step 3.5 Flash

Updated November 21, 2026. Rank says Mistral Large 4 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

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

56.9/100

Supported · Public rank #67

Conditional range 51.2–62.5

Model B
StepFun logo

StepFun

47.7/100

Supported · Public rank #104

Conditional range 36.8–58.7

API price per 1M tokens

Mistral Large 4: $0.70 input / $2.10 output

Step 3.5 Flash: $0.10 input / $0.30 output

Context window

Mistral Large 4: 1M

Step 3.5 Flash: 256K

Released

Mistral Large 4: October 6, 2026

Step 3.5 Flash: February 1, 2026

Shared results
0
Mistral Large 4 only
11
Step 3.5 Flash only
3
Like-for-like categories
1 / 8
Supported: Mistral Large 4 and Step 3.5 Flash. 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.

  • Long documents

    Prompts that approach the documented context limit

    Mistral Large 4

    Mistral Large 4 has the larger documented context window.

    Confidence: documented
  • Chat turn cost

    1K fresh input + 500 output tokens

    Step 3.5 Flash

    Step 3.5 Flash 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

    Step 3.5 Flash

    Step 3.5 Flash has the lower estimated token cost for this stated workload. Step 3.5 Flash has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback
Show secondary and unsupported calls
  • Repository review cost

    50K fresh input + 3K output tokens

    Step 3.5 Flash

    Step 3.5 Flash 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

    Step 3.5 Flash 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

    Step 3.5 Flash 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.

63.2Mistral Large 447.1Step 3.5 Flash

Directional only · BenchAlign v6.0

Mistral Large 4 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.

Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

What is actually comparable

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

4 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 v6.0 lane in every category, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence. Directional and not-comparable rows remain visible, but they never receive a winner.

Reasoning

Like-for-like
Mistral Large 4
56.0
Supported · #57/161
Step 3.5 Flash
45.5
Supported · #96/161
Basis
BenchAlign v6.0 lane · 1 vs 0 public rows
Reading
Mistral Large 4 leads · intervals overlap

Agentic

Directional only
Mistral Large 4
56.2
Supported · #74/179
Step 3.5 Flash
50.5
Estimated · #101/179
Basis
BenchAlign v6.0 lane · 8 vs 0 public rows
Reading
Directional only

Coding

Directional only
Mistral Large 4
63.2
Supported · #43/179
Step 3.5 Flash
47.1
Estimated · #107/179
Basis
BenchAlign v6.0 lane · 2 vs 2 public rows
Reading
Directional only

Instruction following

Directional only
Mistral Large 4
53.5
Estimated · #62/143
Step 3.5 Flash
46.3
Estimated · #90/143
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Directional only

Math

Directional only
Mistral Large 4
55.5
Estimated · #48/125
Step 3.5 Flash
47.5
Estimated · #74/125
Basis
BenchAlign v6.0 lane · 0 vs 1 public rows
Reading
Directional only

Multimodal

Not comparable
Mistral Large 4
50.8
Estimated · #77/119
Step 3.5 Flash
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Knowledge

Not comparable
Mistral Large 4
48.1
Estimated · #96/158
Step 3.5 Flash
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Multilingual

Not comparable
Mistral Large 4
Not ranked
Step 3.5 Flash
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Ranks count the models scored in each category’s BenchAlign v6.0 lane, so denominators differ by category. 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
$0.00175
Fits in one request
Step 3.5 Flash
$0.00025
Fits in one request

Step 3.5 Flash has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Mistral Large 4
$0.0413
Fits in one request
Step 3.5 Flash
$0.0059
Fits in one request

Step 3.5 Flash 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
$0.049
Fits in one request
Step 3.5 Flash
$0.025
Fits in one request
Cached input priced at the published list-input rate

Step 3.5 Flash has the lower modeled cost

Step 3.5 Flash has no published cached-input rate, so cached tokens use its listed input rate.

Your workload

Enter a month of tokens to price it at both models’ listed API rates.

Mistral Large 4
$11.20
per month
Step 3.5 Flash
$1.60
per month

Standard listed rates, no batch or volume discounts.

Cached input falls back to the list input rate only where a cached rate is unpublished

Price against score, among all priced models

Overall score against output price per 1M tokens, one model per family. Pricing as of November 20, 2026.

Mistral Large 4Step 3.5 Flash

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • 5 cheaper models score at least as high as Mistral Large 4. The nearest is DeepSeek V4.1 Flash 1017 (score 70.0, $1.20 per 1M output tokens).
  • Step 3.5 Flash is on the efficiency frontier: no cheaper model scores at least as high.

Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.

See Mistral Large 4 on the full price vs performance chart

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

API model ID

Mistral Large 4

Not sourced

Step 3.5 Flash

Not sourced

Cached-input rate

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

Mistral Large 4

$0.07 per 1M cached input tokens

Mistral AI: Mistral Large 4 is now open weight

Step 3.5 Flash

Not published

Provider availability

Mistral Large 4

Not sourced

Step 3.5 Flash

Not sourced

Reasoning profile

Mistral Large 4

Hybrid

Step 3.5 Flash

Non-Reasoning

Weight access

Mistral Large 4

Open Weight

Step 3.5 Flash

Open Weight

License

Mistral Large 4

Open Weight

Step 3.5 Flash

Open Weight

Release date

Mistral Large 4

2026-10-06

Step 3.5 Flash

2026-02-01

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: $0.0413 vs $0.0059. Cache-heavy agent loop: $0.049 vs $0.025.
Context tradeoff
Mistral Large 4 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Mistral Large 4 or Step 3.5 Flash?

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 3.5 Flash?

Mistral Large 4 scores higher for coding on the public lane, 63.2 to 47.1. Step 3.5 Flash 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, Mistral Large 4 or Step 3.5 Flash?

Mistral Large 4 scores higher for agentic tasks on the public lane, 56.2 to 50.5. Step 3.5 Flash 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, Mistral Large 4 or Step 3.5 Flash?

For the stated presets, chat costs $0.00175 on Mistral Large 4 and $0.00025 on Step 3.5 Flash; repository review costs $0.0413 and $0.0059; the cache-heavy agent loop costs $0.049 and $0.025. Step 3.5 Flash has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Mistral Large 4 or Step 3.5 Flash?

Mistral Large 4 has the larger documented context window: 1M, compared with 256K.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Mistral Large 4
API / mo$2,100
Self-host / mo$37,843
Break-evenNot reached at 70% load
Step 3.5 Flash
API / mo$300
Self-host / mo$6,990
Break-evenNot reached at 70% load
Model the full break-even

Benchmark evidence

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

Browse raw public benchmark evidence14 rows

Agentic

  • Terminal-Bench 4.1

    Mistral Large 427.60%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • Finch

    Mistral Large 473.3%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • b3 Agent Security

    Mistral Large 497.1%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • Cyber Misuse Refusal

    Mistral Large 496.6%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • Cybench

    Mistral Large 493.0%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • BrowseComp

    Mistral Large 484.5%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • Finance Agent v2

    Mistral Large 454.7%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • CWE-bench

    Mistral Large 445.6%
    Source
    Step 3.5 Flash—

    Not directly comparable

Coding

  • Vibe Code Bench

    Mistral Large 478.40%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • FrontierCode 2.0

    Mistral Large 419.7%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • SWE-bench Verified

    Mistral Large 4—
    Step 3.5 Flash74.4%
    Source

    Not directly comparable

  • LiveCodeBench v6

    Mistral Large 4—
    Step 3.5 Flash86.4%
    Source

    Not directly comparable

Reasoning

  • STEMBench

    Mistral Large 42.50
    Source
    Step 3.5 Flash—

    Not directly comparable

Math

  • AIME 2025

    Mistral Large 4—
    Step 3.5 Flash97.3%
    Source

    Not directly comparable

14 public results · 0 shared

Watch Mistral Large 4 vs Step 3.5 Flash

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

Read a sample issue

Join 7,000+ subscribers.

Last updated November 21, 2026