Agentic
Not comparable- GPT-5.4 Pro
- 89.3
- Mistral Medium 3
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Model comparison
GPT-5.4 Pro vs Mistral Medium 3
Updated July 30, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
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 Pro
GPT-5.4 Pro has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Mistral Medium 3
Mistral Medium 3 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 Medium 3
Mistral Medium 3 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
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. Mistral Medium 3 does not fit this workload in one request. GPT-5.4 Pro has no published cached-input rate, so cached tokens use its listed input rate. Mistral Medium 3 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
11 GPT-5.4 Pro only
- Shared results
- 0
- GPT-5.4 Pro only
- 11
- Mistral Medium 3 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.
Coding
Not comparable- GPT-5.4 Pro
- Not measured
- Mistral Medium 3
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Reasoning
Not comparable- GPT-5.4 Pro
- 83.3
- Mistral Medium 3
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- GPT-5.4 Pro
- 58.7
- Mistral Medium 3
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- GPT-5.4 Pro
- 46.9
- Mistral Medium 3
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- GPT-5.4 Pro
- Not measured
- Mistral Medium 3
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- GPT-5.4 Pro
- 94.0
- Mistral Medium 3
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- GPT-5.4 Pro
- Not measured
- Mistral Medium 3
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | GPT-5.4 Pro | Mistral Medium 3 | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 89.3 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Coding | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Reasoning | 83.3 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Knowledge | 58.7 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Math | 46.9 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | 94.0 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 rows | 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 Pro
- $0.12
- Fits in one request
- Mistral Medium 3
- $0.0014
- Fits in one request
Mistral Medium 3 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- GPT-5.4 Pro
- $2.04
- Fits in one request
- Mistral Medium 3
- $0.026
- Fits in one request
Mistral Medium 3 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 Pro
- $8.40
- Fits in one request
- Cached input priced at the published list-input rate
- Mistral Medium 3
- $0.108
- Does not fit in one request
- Cached input priced at the published list-input rate
Mistral Medium 3 does not fit this workload in one request. GPT-5.4 Pro has no published cached-input rate, so cached tokens use its listed input rate. Mistral Medium 3 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.
SpecificationGPT-5.4 ProMistral Medium 3
Context window
Maximum documented context; output-token limits may be lower.
GPT-5.4 Pro
Mistral Medium 3
128K
API model ID
GPT-5.4 Pro
gpt-5.4-pro
OpenAI GPT-5.4 Pro model documentationMistral Medium 3
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 Pro
Not published
OpenAI pricingMistral Medium 3
Not published
Documented inputs
GPT-5.4 Pro
text, image
OpenAI model catalogMistral Medium 3
Not sourced
Documented outputs
GPT-5.4 Pro
Mistral Medium 3
Not sourced
Provider availability
GPT-5.4 Pro
Generally Available · OpenAI Responses API
OpenAI model catalogMistral Medium 3
Not sourced
Reasoning profile
GPT-5.4 Pro
Reasoning
Mistral Medium 3
Non-Reasoning
Weight access
GPT-5.4 Pro
Proprietary
Mistral Medium 3
Proprietary
License
GPT-5.4 Pro
Proprietary
Mistral Medium 3
Proprietary
Release date
GPT-5.4 Pro
2026-03-05
Mistral Medium 3
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: $2.04 vs $0.026. Cache-heavy agent loop: $8.40 vs $0.108.
- Context tradeoff
- GPT-5.4 Pro 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 evidence11 rows
Agentic
BrowseComp
GPT-5.4 Pro89.3%SourceMistral Medium 3—Not directly comparable
Reasoning
ARC-AGI-2
GPT-5.4 Pro83.3%SourceMistral Medium 3—Not directly comparable
Knowledge
HLE
GPT-5.4 Pro58.7%SourceMistral Medium 3—Not directly comparable
FrontierScience
GPT-5.4 Pro36.7%SourceMistral Medium 3—Not directly comparable
FrontierScience Research
GPT-5.4 Pro36.7%SourceMistral Medium 3—Not directly comparable
HLE w/o tools
GPT-5.4 Pro42.7%SourceMistral Medium 3—Not directly comparable
Math
IPhO 2025 (Theory)
GPT-5.4 Pro93.5%SourceMistral Medium 3—Not directly comparable
FrontierMath (legacy)
GPT-5.4 Pro50%SourceMistral Medium 3—Not directly comparable
FrontierMath v2 (Tiers 1-3)
GPT-5.4 Pro50.000%SourceMistral Medium 3—Not directly comparable
FrontierMath v2 (Tier 4)
GPT-5.4 Pro37.500%SourceMistral Medium 3—Not directly comparable
Multimodal
MMMU-Pro
GPT-5.4 Pro94%SourceMistral Medium 3—Not directly comparable
Frequently asked questions
Which is better, GPT-5.4 Pro or Mistral Medium 3?
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 Pro or Mistral Medium 3?
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 Pro or Mistral Medium 3?
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 Pro or Mistral Medium 3?
For the stated presets, chat costs $0.12 on GPT-5.4 Pro and $0.0014 on Mistral Medium 3; repository review costs $2.04 and $0.026; the cache-heavy agent loop costs $8.40 and $0.108. Mistral Medium 3 does not fit this workload in one request. GPT-5.4 Pro has no published cached-input rate, so cached tokens use its listed input rate. Mistral Medium 3 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, GPT-5.4 Pro or Mistral Medium 3?
GPT-5.4 Pro has the larger documented context window: 1.05M, compared with 128K.
Related comparisons
Last updated July 30, 2026
Watch GPT-5.4 Pro vs Mistral Medium 3
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.