Skip to main content
BenchLM
Advertise

Model comparison

GPT-5.4 vs Mistral Small 4 (Reasoning)

Updated July 31, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

GPT-5.4

OpenAI

73.2/100

Supported · Public rank #10

90% interval 70.3–76.2

Mistral Small 4 (Reasoning)

Mistral

—

Evidence status unavailable

90% interval unavailable

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 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.

  • Long documents

    Prompts that approach the documented context limit

    GPT-5.4

    GPT-5.4 has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    Mistral Small 4 (Reasoning)

    Mistral Small 4 (Reasoning) 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 Small 4 (Reasoning)

    Mistral Small 4 (Reasoning) has the lower estimated token cost for this stated workload. Mistral Small 4 (Reasoning) 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

    Mistral Small 4 (Reasoning)

    Mistral Small 4 (Reasoning) 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

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
0
GPT-5.4 only
37
Mistral Small 4 (Reasoning) only
0
Like-for-like categories
0 / 8

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.

Agentic

Not comparable
GPT-5.4
77.2
Mistral Small 4 (Reasoning)
Not measured
Weighted basis
3 vs 0 rows
Reading
Not comparable

Coding

Not comparable
GPT-5.4
57.7
Mistral Small 4 (Reasoning)
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Reasoning

Not comparable
GPT-5.4
74.0
Mistral Small 4 (Reasoning)
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
GPT-5.4
57.6
Mistral Small 4 (Reasoning)
Not measured
Weighted basis
2 vs 0 rows
Reading
Not comparable

Math

Not comparable
GPT-5.4
42.5
Mistral Small 4 (Reasoning)
Not measured
Weighted basis
2 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
GPT-5.4
Not measured
Mistral Small 4 (Reasoning)
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
GPT-5.4
73.2
Mistral Small 4 (Reasoning)
Not measured
Weighted basis
3 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
GPT-5.4
Not measured
Mistral Small 4 (Reasoning)
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.

A shared-evidence shape is not available.

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

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-5.4
$0.01
Fits in one request
Mistral Small 4 (Reasoning)
$0.00045
Fits in one request

Mistral Small 4 (Reasoning) has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

GPT-5.4
$0.17
Fits in one request
Mistral Small 4 (Reasoning)
$0.0093
Fits in one request

Mistral Small 4 (Reasoning) 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-5.4
$0.25
Fits in one request
Mistral Small 4 (Reasoning)
$0.039
Fits in one request
Cached input priced at the published list-input rate

Mistral Small 4 (Reasoning) has the lower modeled cost

Mistral Small 4 (Reasoning) has no published cached-input rate, so cached tokens use its listed input rate.

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-5.4

1.05M

OpenAI pricing

Mistral Small 4 (Reasoning)

256K

API model ID

GPT-5.4

gpt-5.4

OpenAI pricing

Mistral Small 4 (Reasoning)

Not sourced

Cached-input rate

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

GPT-5.4

$0.25 per 1M cached input tokens

OpenAI pricing

Mistral Small 4 (Reasoning)

Not published

Documented inputs

GPT-5.4

Not sourced

Mistral Small 4 (Reasoning)

Not sourced

Documented outputs

GPT-5.4

Not sourced

Mistral Small 4 (Reasoning)

Not sourced

Provider availability

GPT-5.4

Not sourced

Mistral Small 4 (Reasoning)

Not sourced

Reasoning profile

GPT-5.4

Reasoning

Mistral Small 4 (Reasoning)

Reasoning

Weight access

GPT-5.4

Proprietary

Mistral Small 4 (Reasoning)

Open Weight

License

GPT-5.4

Proprietary

Mistral Small 4 (Reasoning)

Open Weight

Release date

GPT-5.4

2026-03-05

Mistral Small 4 (Reasoning)

2026-02-20

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: $0.17 vs $0.0093. Cache-heavy agent loop: $0.25 vs $0.039.
Context tradeoff
GPT-5.4 has the larger documented window (1.05M).

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 evidence37 rows

Agentic

  • Terminal-Bench 2.0

    GPT-5.475.1%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • CyberGym

    GPT-5.479.0%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • BrowseComp

    GPT-5.482.7%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • OSWorld-Verified

    GPT-5.475%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • MCP Atlas

    GPT-5.470.6%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • Toolathlon

    GPT-5.454.6%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • τ²-bench results

    GPT-5.498.9%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • Claw-Eval

    GPT-5.460.3%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • DeepSearchQA

    GPT-5.473.6%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • Gert Labs

    GPT-5.464.89%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • ResearchClawBench

    GPT-5.415.3%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • JobBench

    GPT-5.438.9%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • ExploitGym

    GPT-5.46.0%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

Coding

  • LiveCodeBench Pro

    GPT-5.487.5%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • SWE-bench Pro

    GPT-5.457.7%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • React Native Evals

    GPT-5.485.3%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • Vibe Code Bench

    GPT-5.467.42%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

Reasoning

  • ARC-AGI-2

    GPT-5.474.0%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • ARC-AGI-3

    GPT-5.40.2%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

Knowledge

  • GPQA

    GPT-5.492.8%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • HLE

    GPT-5.452.1%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • HLE w/o tools

    GPT-5.439.8%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • GPQA-D

    GPT-5.492.8%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • HealthBench Hard

    GPT-5.440.1%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • MedXpertQA (Text)

    GPT-5.459.6%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • HealthBench Professional

    GPT-5.448.1%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    GPT-5.447.600%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    GPT-5.427.100%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

Multimodal

  • MMMU-Pro

    GPT-5.481.2%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • OfficeQA Pro

    GPT-5.453.2%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • MMMU-Pro w/ Python

    GPT-5.482.1%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • CharXiv

    GPT-5.482.8%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • ERQA

    GPT-5.465.4%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • SimpleVQA

    GPT-5.461.1%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • ScreenSpot Pro

    GPT-5.485.4%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • ZeroBench

    GPT-5.441.0%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

  • MedXpertQA (MM)

    GPT-5.477.1%
    Source
    Mistral Small 4 (Reasoning)—

    Not directly comparable

Frequently asked questions

Which is better, GPT-5.4 or Mistral Small 4 (Reasoning)?

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-5.4 or Mistral Small 4 (Reasoning)?

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, GPT-5.4 or Mistral Small 4 (Reasoning)?

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, GPT-5.4 or Mistral Small 4 (Reasoning)?

For the stated presets, chat costs $0.01 on GPT-5.4 and $0.00045 on Mistral Small 4 (Reasoning); repository review costs $0.17 and $0.0093; the cache-heavy agent loop costs $0.25 and $0.039. Mistral Small 4 (Reasoning) has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, GPT-5.4 or Mistral Small 4 (Reasoning)?

GPT-5.4 has the larger documented context window: 1.05M, compared with 256K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated July 31, 2026

Watch GPT-5.4 vs Mistral Small 4 (Reasoning)

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

Read a sample issue

Join 2,000+ readers.