Long documents
Prompts that approach the documented context limit
Mistral Small 4
Mistral Small 4 has the larger documented context window.
Confidence: documented
Mistral Medium 3 vs Mistral Small 4
Updated October 29, 2026. Rank says Mistral Small 4 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Share or export
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.
- Shared results
- 0
- Mistral Medium 3 only
- 1
- Mistral Small 4 only
- 0
- Like-for-like categories
- 0 / 8
Estimated: Mistral Medium 3 and Mistral Small 4. 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 Small 4
Mistral Small 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 Small 4
Mistral Small 4 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesCoding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Mistral Medium 3 is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limitedAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Mistral Medium 3 is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limitedCache-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. Mistral Medium 3 has no published cached-input rate, so cached tokens use its listed input rate. Mistral Small 4 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
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 Medium 325.9Mistral Small 4
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.
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.
1 Mistral Medium 3 only
2 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 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
Directional only- Mistral Medium 3
- 28.9
- Estimated · #155/179
- Mistral Small 4
- 36.6
- Estimated · #128/179
- Basis
- BenchAlign v5.8 lane · 0 vs 0 public rows
- Reading
- Directional only
Instruction following
Directional only- Mistral Medium 3
- 45.5
- #112/157
- Mistral Small 4
- 57.1
- #92/157
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Directional only
Agentic
Not comparable- Mistral Medium 3
- Not ranked
- Mistral Small 4
- 24.5
- Estimated · #117/135
- Basis
- BenchAlign v5.8 lane · 0 vs 0 public rows
- Reading
- Not comparable
Coding
Not comparable- Mistral Medium 3
- Not ranked
- Mistral Small 4
- 25.9
- Estimated · #120/156
- Basis
- BenchAlign v5.8 lane · 1 vs 0 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Mistral Medium 3
- 46.5
- Unranked · 2 rankable rows
- Mistral Small 4
- 59.1
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Mistral Medium 3
- 43.4
- Unranked · 1 rankable row
- Mistral Small 4
- 48.9
- Unranked · 1 rankable row
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Mistral Medium 3
- Not ranked
- Mistral Small 4
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Mistral Medium 3
- Not ranked
- Mistral Small 4
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Mistral Medium 3 | Mistral Small 4 | Basis | Reading |
|---|---|---|---|---|
| Knowledge | 28.9Estimated · #155/179 | 36.6Estimated · #128/179 | Directional onlyBenchAlign v5.8 lane · 0 vs 0 public rows | Directional only |
| Instruction following | 45.5#112/157 | 57.1#92/157 | Directional onlyProvisional lane · 0 vs 0 weighted rows | Directional only |
| Agentic | Not ranked | 24.5Estimated · #117/135 | Not comparableBenchAlign v5.8 lane · 0 vs 0 public rows | Not comparable |
| Coding | Not ranked | 25.9Estimated · #120/156 | Not comparableBenchAlign v5.8 lane · 1 vs 0 public rows | Not comparable |
| Reasoning | 46.5Unranked · 2 rankable rows | 59.1Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 43.4Unranked · 1 rankable row | 48.9Unranked · 1 rankable row | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | 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.
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 Medium 3
- $0.0014
- Fits in one request
- Mistral Small 4
- $0.00045
- Fits in one request
Mistral Small 4 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Mistral Medium 3
- $0.026
- Fits in one request
- Mistral Small 4
- $0.0093
- Fits in one request
Mistral Small 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 Medium 3
- $0.108
- Does not fit in one request
- Cached input priced at the published list-input rate
- Mistral Small 4
- $0.039
- Fits in one request
- Cached input priced at the published list-input rate
Mistral Medium 3 does not fit this workload in one request. Mistral Medium 3 has no published cached-input rate, so cached tokens use its listed input rate. Mistral Small 4 has no published cached-input rate, so cached tokens use its listed input rate.
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.
SpecificationMistral Medium 3Mistral Small 4
Context window
Maximum documented context; output-token limits may be lower.
Mistral Medium 3
128K
Mistral Small 4
256K
API model ID
Mistral Medium 3
Not sourced
Mistral Small 4
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Mistral Medium 3
Not published
Mistral Small 4
Not published
Documented inputs
Mistral Medium 3
Not sourced
Mistral Small 4
Not sourced
Documented outputs
Mistral Medium 3
Not sourced
Mistral Small 4
Not sourced
Provider availability
Mistral Medium 3
Not sourced
Mistral Small 4
Not sourced
Reasoning profile
Mistral Medium 3
Non-Reasoning
Mistral Small 4
Non-Reasoning
Weight access
Mistral Medium 3
Proprietary
Mistral Small 4
Open Weight
License
Mistral Medium 3
Proprietary
Mistral Small 4
Open Weight
Release date
Mistral Medium 3
2025-05-07
Mistral Small 4
2026-03-16
If you already use one of these models
- Deployment change
- Both entries list Mistral as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- 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: $0.026 vs $0.0093. Cache-heavy agent loop: $0.108 vs $0.039.
- Context tradeoff
- Mistral Small 4 has the larger documented window (256K).
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Mistral Medium 3 or Mistral Small 4?
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 Medium 3 or Mistral Small 4?
Mistral Medium 3 is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, Mistral Medium 3 or Mistral Small 4?
Mistral Medium 3 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, Mistral Medium 3 or Mistral Small 4?
For the stated presets, chat costs $0.0014 on Mistral Medium 3 and $0.00045 on Mistral Small 4; repository review costs $0.026 and $0.0093; the cache-heavy agent loop costs $0.108 and $0.039. Mistral Medium 3 does not fit this workload in one request. Mistral Medium 3 has no published cached-input rate, so cached tokens use its listed input rate. Mistral Small 4 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Mistral Medium 3 or Mistral Small 4?
Mistral Small 4 has the larger documented context window: 256K, compared with 128K.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Mistral Medium 3
API / mo$1,800
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Mistral Small 4
API / mo$563
Self-host / mo$3,495
Break-even409M/day
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence1 rows
Coding
LiveCodeBench v6
Mistral Medium 330.3%SourceMistral Small 4—Not directly comparable
1 public result · 0 shared
Watch Mistral Medium 3 vs Mistral Small 4
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 6,100+ subscribers.
Last updated October 29, 2026