Long documents
Prompts that approach the documented context limit
Mistral Medium 3.5 128B
Mistral Medium 3.5 128B has the larger documented context window.
Confidence: documented
DeepSeek V3.2 vs Mistral Medium 3.5 128B
Updated October 25, 2026. Rank says DeepSeek V3.2 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Share or export
Decision reading
DeepSeek V3.2 has the higher public point estimate, 50.25 versus 33.57. Their conditional score ranges overlap. These ranges do not establish rank confidence. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Model B
Mistral
33.57/100
Estimated · Public rank #167
Conditional range 19.2–47.9
- Shared results
- 1
- DeepSeek V3.2 only
- 4
- Mistral Medium 3.5 128B only
- 6
- Like-for-like categories
- 0 / 8
Supported: DeepSeek V3.2 · Estimated: Mistral Medium 3.5 128B. 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
DeepSeek V3.2
DeepSeek V3.2 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
DeepSeek V3.2
DeepSeek V3.2 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
DeepSeek V3.2 and Mistral Medium 3.5 128B are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limitedAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
DeepSeek V3.2 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. DeepSeek V3.2 does not fit this workload in one request. Mistral Medium 3.5 128B 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.
28.7DeepSeek V3.222.9Mistral Medium 3.5 128B
Directional only · BenchAlign v5.8
DeepSeek V3.2 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
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
4 DeepSeek V3.2 only
1 Shared
6 Mistral Medium 3.5 128B only
3 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.
Coding
Directional only- DeepSeek V3.2
- 28.7
- Estimated · #102/153
- Mistral Medium 3.5 128B
- 22.9
- Estimated · #117/153
- Basis
- BenchAlign v5.8 lane · 2 vs 2 public rows
- Reading
- Directional only
Knowledge
Directional only- DeepSeek V3.2
- 41.5
- Estimated · #112/187
- Mistral Medium 3.5 128B
- 31.2
- Supported · #151/187
- Basis
- BenchAlign v5.8 lane · 0 vs 2 public rows
- Reading
- Directional only
Instruction following
Directional only- DeepSeek V3.2
- 58.2
- #85/153
- Mistral Medium 3.5 128B
- 84.0
- #54/153
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Directional only
Agentic
Not comparable- DeepSeek V3.2
- Not ranked
- Mistral Medium 3.5 128B
- 20.0
- Supported · #114/132
- Basis
- BenchAlign v5.8 lane · 3 vs 3 public rows
- Reading
- Not comparable
Reasoning
Not comparable- DeepSeek V3.2
- 56.4
- Unranked · 2 rankable rows
- Mistral Medium 3.5 128B
- 72.6
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- DeepSeek V3.2
- Not ranked
- Mistral Medium 3.5 128B
- 61.0
- Unranked · 1 rankable row
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- DeepSeek V3.2
- Not ranked
- Mistral Medium 3.5 128B
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- DeepSeek V3.2
- Not ranked
- Mistral Medium 3.5 128B
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | DeepSeek V3.2 | Mistral Medium 3.5 128B | Basis | Reading |
|---|---|---|---|---|
| Coding | 28.7Estimated · #102/153 | 22.9Estimated · #117/153 | Directional onlyBenchAlign v5.8 lane · 2 vs 2 public rows | Directional only |
| Knowledge | 41.5Estimated · #112/187 | 31.2Supported · #151/187 | Directional onlyBenchAlign v5.8 lane · 0 vs 2 public rows | Directional only |
| Instruction following | 58.2#85/153 | 84.0#54/153 | Directional onlyProvisional lane · 0 vs 0 weighted rows | Directional only |
| Agentic | Not ranked | 20.0Supported · #114/132 | Not comparableBenchAlign v5.8 lane · 3 vs 3 public rows | Not comparable |
| Reasoning | 56.4Unranked · 2 rankable rows | 72.6Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | 61.0Unranked · 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.
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
- DeepSeek V3.2
- $0.00049
- Fits in one request
- Mistral Medium 3.5 128B
- $0.00525
- Fits in one request
DeepSeek V3.2 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- DeepSeek V3.2
- $0.01526
- Fits in one request
- Mistral Medium 3.5 128B
- $0.0975
- Fits in one request
DeepSeek V3.2 has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- DeepSeek V3.2
- $0.0154
- Does not fit in one request
- Mistral Medium 3.5 128B
- $0.405
- Fits in one request
- Cached input priced at the published list-input rate
DeepSeek V3.2 does not fit this workload in one request. Mistral Medium 3.5 128B 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.
SpecificationDeepSeek V3.2Mistral Medium 3.5 128B
Context window
Maximum documented context; output-token limits may be lower.
DeepSeek V3.2
128K
Mistral Medium 3.5 128B
256K
API model ID
DeepSeek V3.2
Not sourced
Mistral Medium 3.5 128B
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
DeepSeek V3.2
$0.028 per 1M cached input tokens
Mistral Medium 3.5 128B
Not published
Documented inputs
DeepSeek V3.2
Not sourced
Mistral Medium 3.5 128B
Not sourced
Documented outputs
DeepSeek V3.2
Not sourced
Mistral Medium 3.5 128B
Not sourced
Provider availability
DeepSeek V3.2
Not sourced
Mistral Medium 3.5 128B
Not sourced
Reasoning profile
DeepSeek V3.2
Non-Reasoning
Mistral Medium 3.5 128B
Reasoning
Weight access
DeepSeek V3.2
Open Weight
Mistral Medium 3.5 128B
Open Weight
License
DeepSeek V3.2
Open Weight
Mistral Medium 3.5 128B
Open Weight
Release date
DeepSeek V3.2
2025-12-01
Mistral Medium 3.5 128B
2026-04-29
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
- DeepSeek V3.2 has the higher public point estimate, 50.25 versus 33.57. Their conditional score ranges overlap. These ranges do not establish rank confidence.
- Workload cost
- Repository review: $0.01526 vs $0.0975. Cache-heavy agent loop: $0.0154 vs $0.405.
- Context tradeoff
- Mistral Medium 3.5 128B has the larger documented window (256K).
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, DeepSeek V3.2 or Mistral Medium 3.5 128B?
DeepSeek V3.2 has the higher public point estimate, 50.25 versus 33.57. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, DeepSeek V3.2 or Mistral Medium 3.5 128B?
DeepSeek V3.2 scores higher for coding on the public lane, 28.7 to 22.9. DeepSeek V3.2 and Mistral Medium 3.5 128B are 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, DeepSeek V3.2 or Mistral Medium 3.5 128B?
DeepSeek V3.2 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, DeepSeek V3.2 or Mistral Medium 3.5 128B?
For the stated presets, chat costs $0.00049 on DeepSeek V3.2 and $0.00525 on Mistral Medium 3.5 128B; repository review costs $0.01526 and $0.0975; the cache-heavy agent loop costs $0.0154 and $0.405. DeepSeek V3.2 does not fit this workload in one request. Mistral Medium 3.5 128B has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, DeepSeek V3.2 or Mistral Medium 3.5 128B?
Mistral Medium 3.5 128B 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.
DeepSeek V3.2
API / mo$525
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Mistral Medium 3.5 128B
API / mo$6,750
Self-host / mo$6,990
Break-even71M/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 evidence11 rows
Agentic
Claw-Eval
DeepSeek V3.240.2%SourceMistral Medium 3.5 128B—Not directly comparable
VITA-Bench
DeepSeek V3.218.5%SourceMistral Medium 3.5 128B—Not directly comparable
Gert Labs
Shared sourceDeepSeek V3.229.57%Mistral Medium 3.5 128B39.10%Mistral Medium 3.5 128B leads this result
τ³-bench results
DeepSeek V3.2—Mistral Medium 3.5 128B91.4%SourceNot directly comparable
Terminal-Bench 2.1 (Vals)
DeepSeek V3.2—Mistral Medium 3.5 128B39.0%SourceNot directly comparable
Coding
SWE-Rebench
DeepSeek V3.260.9%SourceMistral Medium 3.5 128B—Not directly comparable
React Native Evals
DeepSeek V3.271.5%SourceMistral Medium 3.5 128B—Not directly comparable
SWE-bench Verified
DeepSeek V3.2—Mistral Medium 3.5 128B77.6%SourceNot directly comparable
SWE-bench (Vals)
DeepSeek V3.2—Mistral Medium 3.5 128B66.4%SourceNot directly comparable
Knowledge
11 public results · 1 shared
Watch DeepSeek V3.2 vs Mistral Medium 3.5 128B
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 25, 2026