Updated November 7, 2026. Rank says DeepSeek V4.1 Flash 1017 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
DeepSeek V4.1 Flash 1017 has the higher public point estimate, 65.41 versus 59.06. Their conditional score ranges overlap. These ranges do not establish rank confidence. 8 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Thinking Machines Lab
59.06/100
Estimated · Public rank #56
Conditional range 44.7–73.4
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.
Code generation, repair, and software-engineering tasks
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 has the higher public coding point estimate, 63.3 to 59.7, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Tool use, computer use, and multi-step task completion
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 has the higher public agentic point estimate, 61.7 to 59.9, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
1K fresh input + 500 output tokens
Inkling 2 Small
Inkling 2 Small has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Inkling 2 Small
Inkling 2 Small has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
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.
Like-for-like · BenchAlign v5.8
DeepSeek V4.1 Flash 1017 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.
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
GPQAKnowledge
Normalized gap 2.1Each 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.
| Category | DeepSeek V4.1 Flash 1017 | Inkling 2 Small | Basis | Reading |
|---|---|---|---|---|
| Agentic | 61.7Supported · #21/131 | 59.9Supported · #26/131 | Like-for-likeBenchAlign v5.8 lane · 11 vs 5 public rows | DeepSeek V4.1 Flash 1017 leads · intervals overlap |
| Coding | 63.3Supported · #14/157 | 59.7Supported · #20/157 | Like-for-likeBenchAlign v5.8 lane · 10 vs 6 public rows | DeepSeek V4.1 Flash 1017 leads · intervals overlap |
| Knowledge | 64.5Supported · #36/178 | 60.4Estimated · #46/178 | Directional onlyBenchAlign v5.8 lane · 3 vs 2 public rows | Directional only |
| Reasoning | 80.8Unranked · 4 rankable rows | 86.1Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Multimodal | 78.0Unranked · 1 rankable row | 86.6#12/59 | Not comparableProvisional lane · 0 vs 1 weighted 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 | 66.5Unranked · 3 rankable rows | 85.9Unranked · 2 rankable rows | Not comparableProvisional lane · 2 vs 1 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.
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.
1K fresh input + 500 output tokens
Inkling 2 Small has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Inkling 2 Small has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
DeepSeek V4.1 Flash 1017 has the lower modeled cost
Costs use the listed standard API rates.
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
DeepSeek V4.1 Flash 1017
Inkling 2 Small
DeepSeek V4.1 Flash 1017
deepseek-flash
DeepSeek models and pricingInkling 2 Small
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
DeepSeek V4.1 Flash 1017
$0.006 per 1M cached input tokens
DeepSeek: Models & PricingInkling 2 Small
$0.03 per 1M cached input tokens
Tinker models and pricingDeepSeek V4.1 Flash 1017
text, image
DeepSeek vision guideInkling 2 Small
Not sourced
DeepSeek V4.1 Flash 1017
Inkling 2 Small
Not sourced
DeepSeek V4.1 Flash 1017
Generally Available · DeepSeek API, open weights
DeepSeek-V4.1-Flash-1017 API changelogInkling 2 Small
Not sourced
DeepSeek V4.1 Flash 1017
Reasoning
Inkling 2 Small
Hybrid
DeepSeek V4.1 Flash 1017
Open Weight
Inkling 2 Small
Proprietary
DeepSeek V4.1 Flash 1017
Open Weight
Inkling 2 Small
Proprietary
DeepSeek V4.1 Flash 1017
2026-10-17
Inkling 2 Small
2026-11-05
DeepSeek V4.1 Flash 1017 has the higher public point estimate, 65.41 versus 59.06. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
DeepSeek V4.1 Flash 1017 has the higher public coding point estimate, 63.3 to 59.7, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
DeepSeek V4.1 Flash 1017 has the higher public agentic tasks point estimate, 61.7 to 59.9, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
For the stated presets, chat costs $0.0009 on DeepSeek V4.1 Flash 1017 and $0.0008 on Inkling 2 Small; repository review costs $0.0186 and $0.018; the cache-heavy agent loop costs $0.0192 and $0.022. Costs use the listed standard API rates.
Both models list the same context window, 1M.
Estimates at 50,000 req/day · 1000 tokens/req average.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 2.1
DeepSeek V4.1 Flash 1017 leads this result
terminalBench3
Not directly comparable
Terminal-Bench 4.0
Not directly comparable
CyberGym
Not directly comparable
ExploitGym
Not directly comparable
HLE w/ tools
Not directly comparable
AutomationBench
Not directly comparable
Agents' Last Exam
Not directly comparable
Terminal-Bench 2.1 (Vals)
Not directly comparable
CWE-bench v1
Not directly comparable
MazeBench
Not directly comparable
BrowseComp
Not directly comparable
DeepSearchQA
Not directly comparable
MCP Atlas
Not directly comparable
JobBench
Not directly comparable
ScarfBench
Not directly comparable
Codeforces
Not directly comparable
Terminal-Bench 2.1
DeepSeek V4.1 Flash 1017 leads this result
terminalBench3
Not directly comparable
DeepSWE
DeepSeek V4.1 Flash 1017 leads this result
ProgramBench
Not directly comparable
NL2Repo
Not directly comparable
OpenHarmony Bench
Not directly comparable
Bug Hunt Bench
Not directly comparable
FrontierCode 2.0
Not directly comparable
SWE-bench Verified
Not directly comparable
SWE Multilingual
Not directly comparable
sweMarathon
Not directly comparable
PostTrainBench v1.2
Not directly comparable
STEMBench
Not directly comparable
JevBench 1.4
Not directly comparable
JevBench 1.5
Not directly comparable
LongBench v2
Not directly comparable
ExtractBench (LlamaIndex)
Not directly comparable
ParseBench
Not directly comparable
Chartography (tools)
DeepSeek V4.1 Flash 1017 leads this result
BabyVision w/ Python
Inkling 2 Small leads this result
ZeroBench w/ Python
Not directly comparable
CharXiv
Not directly comparable
CharXiv w/o tools
Not directly comparable
Chartography (no tools)
Not directly comparable
BabyVision
Not directly comparable
ScreenSpot Pro
Not directly comparable
PerceptionBench
Not directly comparable
MathVision
Not directly comparable
Apex
DeepSeek V4.1 Flash 1017 leads this result
FrontierMath v2 (Tiers 1-3)
Not directly comparable
FrontierMath v2 (Tier 4)
Not directly comparable
HMMT Feb 2026
Not directly comparable
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 November 7, 2026
