Long documents
Prompts that approach the documented context limit
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 has the larger documented context window.
Confidence: documented
DeepSeek V4 Flash 0731 vs Laguna M.1
Updated September 27, 2026. We do not rank this pair: at least one has no public score. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
Share or export
Decision reading
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. 10 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 10
- DeepSeek V4 Flash 0731 only
- 32
- Laguna M.1 only
- 0
- Like-for-like categories
- 0 / 8
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.
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
DeepSeek V4 Flash 0731 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
DeepSeek V4 Flash 0731 and Laguna M.1 are not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limitedChat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-ratesCache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-ratesRepository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
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.
—DeepSeek V4 Flash 073128.5Laguna M.1
Not comparable · BenchAlign v5.7
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.
32 DeepSeek V4 Flash 0731 only
10 Shared
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.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
LiveCodeBench (Vals)Coding
Normalized gap 19.2DeepSeek V4 Flash 0731:87.3%Laguna M.1:68.1%MMLU-Pro (Vals)Knowledge
Normalized gap 17.4DeepSeek V4 Flash 0731:86.2%Laguna M.1:68.8%Terminal-Bench 2.0Agentic
Normalized gap 11.1DeepSeek V4 Flash 0731:56.9%Laguna M.1:45.8%SWE MultilingualCoding
Normalized gap 10.2DeepSeek V4 Flash 0731:73.3%Laguna M.1:63.1%SWE-bench VerifiedCoding
Normalized gap 4.4DeepSeek V4 Flash 0731:79%Laguna M.1:74.6%
Bars run 0–100 on each benchmark’s normalized display scale
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign v5.7 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.
Agentic
Not comparable- DeepSeek V4 Flash 0731
- Not ranked
- Laguna M.1
- Not ranked
- Basis
- BenchAlign v5.7 lane · 11 vs 2 public rows
- Reading
- Not comparable
Coding
Not comparable- DeepSeek V4 Flash 0731
- Not ranked
- Laguna M.1
- 28.5
- Supported · #89/135
- Basis
- BenchAlign v5.7 lane · 15 vs 6 public rows
- Reading
- Not comparable
Reasoning
Not comparable- DeepSeek V4 Flash 0731
- 57.0
- Unranked · 4 rankable rows
- Laguna M.1
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- DeepSeek V4 Flash 0731
- Not ranked
- Laguna M.1
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- DeepSeek V4 Flash 0731
- Not ranked
- Laguna M.1
- Not ranked
- Basis
- BenchAlign v5.7 lane · 8 vs 2 public rows
- Reading
- Not comparable
Multilingual
Not comparable- DeepSeek V4 Flash 0731
- Not ranked
- Laguna M.1
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- DeepSeek V4 Flash 0731
- Not ranked
- Laguna M.1
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- DeepSeek V4 Flash 0731
- 79.9
- Unranked · 4 rankable rows
- Laguna M.1
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
| Category | DeepSeek V4 Flash 0731 | Laguna M.1 | Basis | Reading |
|---|---|---|---|---|
| Agentic | Not ranked | Not ranked | Not comparableBenchAlign v5.7 lane · 11 vs 2 public rows | Not comparable |
| Coding | Not ranked | 28.5Supported · #89/135 | Not comparableBenchAlign v5.7 lane · 15 vs 6 public rows | Not comparable |
| Reasoning | 57.0Unranked · 4 rankable rows | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Knowledge | Not ranked | Not ranked | Not comparableBenchAlign v5.7 lane · 8 vs 2 public rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 79.9Unranked · 4 rankable rows | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.7) 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 V4 Flash 0731
- $0.00028
- Fits in one request
- Laguna M.1
- API rate not published
- Fits in one request
Laguna M.1 has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- DeepSeek V4 Flash 0731
- $0.00784
- Fits in one request
- Laguna M.1
- API rate not published
- Fits in one request
Laguna M.1 has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- DeepSeek V4 Flash 0731
- $0.00616
- Fits in one request
- Laguna M.1
- API rate not published
- Fits in one request
- Cached-input rate unavailable
Laguna M.1 has no comparable published API token 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 V4 Flash 0731Laguna M.1
Context window
Maximum documented context; output-token limits may be lower.
DeepSeek V4 Flash 0731
Laguna M.1
256K
API model ID
DeepSeek V4 Flash 0731
deepseek-v4-flash
DeepSeek-V4.1-Flash releaseLaguna M.1
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
DeepSeek V4 Flash 0731
$0.0028 per 1M cached input tokens
Laguna M.1
No comparable hosted API rate
Documented inputs
DeepSeek V4 Flash 0731
Laguna M.1
Not sourced
Documented outputs
DeepSeek V4 Flash 0731
Laguna M.1
Not sourced
Provider availability
DeepSeek V4 Flash 0731
Deprecated · DeepSeek API
DeepSeek-V4.1-Flash releaseLaguna M.1
Not sourced
Reasoning profile
DeepSeek V4 Flash 0731
Reasoning
Laguna M.1
Reasoning
Weight access
DeepSeek V4 Flash 0731
Open Weight
Laguna M.1
Proprietary
License
DeepSeek V4 Flash 0731
Open Weight
Laguna M.1
Proprietary
Release date
DeepSeek V4 Flash 0731
2026-07-31
Laguna M.1
2026-04-28
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
- At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- DeepSeek V4 Flash 0731 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, DeepSeek V4 Flash 0731 or Laguna M.1?
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, DeepSeek V4 Flash 0731 or Laguna M.1?
DeepSeek V4 Flash 0731 is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, DeepSeek V4 Flash 0731 or Laguna M.1?
DeepSeek V4 Flash 0731 and Laguna M.1 are not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, DeepSeek V4 Flash 0731 or Laguna M.1?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, DeepSeek V4 Flash 0731 or Laguna M.1?
DeepSeek V4 Flash 0731 has the larger documented context window: 1M, compared with 256K.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence42 rows
Agentic
Terminal-Bench 2.0
DeepSeek V4 Flash 073156.9%SourceLaguna M.145.8%SourceDeepSeek V4 Flash 0731 leads this result
BrowseComp
DeepSeek V4 Flash 073173.2%SourceLaguna M.1—Not directly comparable
HLE w/ tools
DeepSeek V4 Flash 073145.1%SourceLaguna M.1—Not directly comparable
MCP Atlas
DeepSeek V4 Flash 073169%SourceLaguna M.1—Not directly comparable
Toolathlon
DeepSeek V4 Flash 073147.8%SourceLaguna M.1—Not directly comparable
Terminal-Bench 2.1
DeepSeek V4 Flash 073182.7%SourceLaguna M.1—Not directly comparable
CyberGym
DeepSeek V4 Flash 073176.7%SourceLaguna M.1—Not directly comparable
Toolathlon-Verified
DeepSeek V4 Flash 073170.3%SourceLaguna M.1—Not directly comparable
Agents' Last Exam
DeepSeek V4 Flash 073125.2%SourceLaguna M.1—Not directly comparable
AutomationBench
DeepSeek V4 Flash 073125.1%SourceLaguna M.1—Not directly comparable
Terminal-Bench 2.1 (Vals)
DeepSeek V4 Flash 073167.0%SourceLaguna M.134.1%SourceDeepSeek V4 Flash 0731 leads this result
Coding
LiveCodeBench Pass@1-COT
DeepSeek V4 Flash 073191.6%SourceLaguna M.1—Not directly comparable
Codeforces
DeepSeek V4 Flash 07313052.0SourceLaguna M.1—Not directly comparable
SWE-bench Verified
DeepSeek V4 Flash 073179%SourceLaguna M.174.6%SourceDeepSeek V4 Flash 0731 leads this result
SWE-bench Pro
DeepSeek V4 Flash 073152.6%SourceLaguna M.149.2%SourceDeepSeek V4 Flash 0731 leads this result
SWE Multilingual
DeepSeek V4 Flash 073173.3%SourceLaguna M.163.1%SourceDeepSeek V4 Flash 0731 leads this result
Terminal-Bench 2.0
DeepSeek V4 Flash 073156.9%SourceLaguna M.145.8%SourceDeepSeek V4 Flash 0731 leads this result
Terminal-Bench 2.1
DeepSeek V4 Flash 073182.7%SourceLaguna M.1—Not directly comparable
NL2Repo
DeepSeek V4 Flash 073154.2%SourceLaguna M.1—Not directly comparable
DeepSWE
DeepSeek V4 Flash 073154.4%SourceLaguna M.1—Not directly comparable
DSBench-FullStack
DeepSeek V4 Flash 073168.7%SourceLaguna M.1—Not directly comparable
DSBench-Hard
DeepSeek V4 Flash 073159.6%SourceLaguna M.1—Not directly comparable
VulcanBench v3
DeepSeek V4 Flash 073188.4%SourceLaguna M.1—Not directly comparable
OpenHarmony Bench
DeepSeek V4 Flash 073153.8%SourceLaguna M.1—Not directly comparable
LiveCodeBench (Vals)
DeepSeek V4 Flash 073187.3%SourceLaguna M.168.1%SourceDeepSeek V4 Flash 0731 leads this result
SWE-bench (Vals)
DeepSeek V4 Flash 073188.8%SourceLaguna M.157.6%SourceDeepSeek V4 Flash 0731 leads this result
Reasoning
MRCR 1M
DeepSeek V4 Flash 073178.7%SourceLaguna M.1—Not directly comparable
CorpusQA 1M
DeepSeek V4 Flash 073160.5%SourceLaguna M.1—Not directly comparable
ARC-AGI-1
DeepSeek V4 Flash 073189.00%SourceLaguna M.1—Not directly comparable
ARC-AGI-2
DeepSeek V4 Flash 073161.4%SourceLaguna M.1—Not directly comparable
Knowledge
MMLU-Pro
DeepSeek V4 Flash 073186.2%SourceLaguna M.1—Not directly comparable
SimpleQA
DeepSeek V4 Flash 073134.1%SourceLaguna M.1—Not directly comparable
Chinese-SimpleQA
DeepSeek V4 Flash 073178.9%SourceLaguna M.1—Not directly comparable
GPQA
DeepSeek V4 Flash 073188.1%SourceLaguna M.1—Not directly comparable
GPQA-D
DeepSeek V4 Flash 073188.1%SourceLaguna M.1—Not directly comparable
HLE
DeepSeek V4 Flash 073134.8%SourceLaguna M.1—Not directly comparable
GPQA Diamond (Vals)
DeepSeek V4 Flash 073189.9%SourceLaguna M.127.0%SourceDeepSeek V4 Flash 0731 leads this result
MMLU-Pro (Vals)
DeepSeek V4 Flash 073186.2%SourceLaguna M.168.8%SourceDeepSeek V4 Flash 0731 leads this result
Math
HMMT Feb 2026
DeepSeek V4 Flash 073194.8%SourceLaguna M.1—Not directly comparable
IMOAnswerBench
DeepSeek V4 Flash 073188.4%SourceLaguna M.1—Not directly comparable
Apex
DeepSeek V4 Flash 073133.0%SourceLaguna M.1—Not directly comparable
Apex Shortlist
DeepSeek V4 Flash 073185.7%SourceLaguna M.1—Not directly comparable
42 public results · 10 shared
Watch DeepSeek V4 Flash 0731 vs Laguna M.1
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.
Last updated September 27, 2026