RankingDeepSeek V4.1 Flash

DeepSeek V4.1 Flash

Compare models

Data updated 22 Nov 2026

DeepSeek V4.1 Flash by DeepSeek is a DeepSeek V4.1 model, released 2026-09-10. This profile collects the published benchmark results and reported effort settings for this model. Configurations are compared on the effort page. Ranks are on the leaderboard.

6 published benchmark measures · 45 measured effort results · 1 benchmark families contribute across 1 task areas. 1 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →

Compare with

Choose a second model and its effort to see both profiles and benchmark differences below.

Compare with

Choose a configuration to compare. The overview below combines evidence across settings and has no model-wide rank.

Model evidence summary

This profile combines published settings. It is not a runnable configuration or a leaderboard rank. Compare measured configurations →

Performance profile

Capabilities

Adjusted comparison score · 0–100
DeepSeek V4.1 Flash capability radarComparison scores from 0 to 100. Unknown capabilities have no point; lines stop at gaps. Hollow points are preliminary. Exact values and support labels follow the chart.AgenticHard reasoningCodingHuman prefKnowledgeMultimodalLong context50100DeepSeek V4.1 Flash · Hard reasoning: 51.5 · Preliminary

Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.

AgenticNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 13/13 scenarios unsupported. Without one publisher: No supported estimate; 15/15 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage; source sensitivity still requires inspection. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

    Hard reasoning1 families · 1 with independent evidence · Preliminary51.5

    1 core families; 59 direct opponents across 10 labs. Needs broader benchmark and opponent support

    Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

    Refit without one family: No supported estimate; 6/6 scenarios unsupported. Without one publisher: No supported estimate; 16/16 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

    Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

    Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

    • ARC-AGI: 69.5 observed win share
      arcprize.org · Source 1
    CodingNo comparable evidenceUnknown

    0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

    Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

    Refit without one family: No supported estimate; 6/6 scenarios unsupported. Without one publisher: No supported estimate; 19/19 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

    Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

    Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

      Human prefNo comparable evidenceUnknown

      0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

      Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

      Refit without one family: No supported estimate; 1/1 scenarios unsupported. Without one publisher: No supported estimate; 1/1 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

      Audit: cross-family and cross-publisher predictions could not be evaluated from the available comparison network. Validation audit.

      Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

        KnowledgeNo comparable evidenceUnknown

        0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

        Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

        Refit without one family: No supported estimate; 4/4 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

        Audit: almost no publisher-held-out comparisons remained estimable. Cross-source validity is unresolved. Validation audit.

        Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

          MultimodalNo comparable evidenceUnknown

          0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

          Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

          Refit without one family: No supported estimate; 8/8 scenarios unsupported. Without one publisher: No supported estimate; 8/8 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

          Audit: limited publisher-held-out coverage. Cross-source validity is unresolved. Validation audit.

          Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

            Long contextNo comparable evidenceUnknown

            0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

            Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

            Refit without one family: No supported estimate; 5/5 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

            Audit: family and publisher holdouts underperformed neutral predictions. Treat this as an exploratory estimate. Validation audit.

            Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

              Scores estimate outcomes against a shared reference panel; they are not accuracy percentages. Sparse or disconnected evidence cannot qualify an overall profile. Open a capability to inspect its evidence.

              Reported effort · Not specified

              Settings reported in this model's published benchmark results, including results outside the aggregate. Effort names are provider-specific. These are not API defaults or equal compute budgets.

              Mixed settings means multiple settings occur in the evidence. Best across efforts means the source selected its best reported result across settings; it does not mean Max. Unspecified settings stay unknown. This model-summary chart combines reported settings. The leaderboard keeps identified configurations separate and excludes unknown effort.

              Inspect each result and its source ↓ · Download effort evidence
              Score contributions and missing evidence

              1 contributing families across 1 capabilities. Fixed reference panels do not change when the catalog expands.

              Capability is fitted jointly across families. Capability estimates below describe different task areas; their weighted sum is not the Capability score.

              Results without reviewed compatibility or a reference match remain in the raw evidence below. Coverage counts only contributing results.

              Model information & shareable badge
              Lab
              DeepSeek
              Catalog status
              api-listed
              Availability
              Documented provider API; distinct September 10 checkpoint. Retired V4 Flash endpoint aliases now route here; historical checkpoints remain separate.
              Family
              DeepSeek V4.1
              Released
              2026-09-10
              Context
              1,000,000 tokens
              License
              —
              Model card
              https://api-docs.deepseek.com/updates/
              Default Capability family coverage
              Documented-evidence family coverage/badge/deepseek-v4.1-flash.svg

              DeepSeek V4.1 Flash measured results by effort setting

              Each row is one published result for one effort setting. Evidence collected 2026-11-22. Compare the effort settings →

              BenchmarkEffortScoreSource
              AA-AnalystAgentMax35.0%Artificial Analysis
              AA-Briefcase EloMax1415Artificial Analysis
              AA-Briefcase EloNon-reasoning1118Artificial Analysis
              AA-LCR v1.1Max84.0%Artificial Analysis
              AA-LCR v1.1Non-reasoning55.3%Artificial Analysis
              ARC-AGI-2High67.5%ARC Prize
              ARC-AGI-2Low60.6%ARC Prize
              ARC-AGI-2Max72.9%ARC Prize
              ARC-AGI-2None1.3%ARC Prize
              ARC-AGI-3 · provider-adapterHigh3.2%ARC Prize
              ARC-AGI-3 · provider-adapterLow3.3%ARC Prize
              ARC-AGI-3 · provider-adapterMax2.7%ARC Prize
              ARC-AGI-3 · provider-adapterNone0.5%ARC Prize
              ARC-AGI-3 · standardHigh0.5%ARC Prize
              ARC-AGI-3 · standardLow0.3%ARC Prize
              ARC-AGI-3 · standardMax0.9%ARC Prize
              ARC-AGI-3 · standardNone0.3%ARC Prize
              Artificial Analysis Cyber IndexMax40.8Artificial Analysis
              AutomationBench-AAMax68.9%Artificial Analysis
              AutomationBench-AANon-reasoning47.8%Artificial Analysis
              CritPtMax14.3%Artificial Analysis
              CritPtNon-reasoning0.3%Artificial Analysis
              FrontierCode 1.1 · extended-devin-cliHigh56.6%Cognition
              FrontierCode 1.1 · main-devin-cliHigh43.9%Cognition
              FrontierCS 2Unspecified14.6%FrontierCS
              GDP.pdf: All-pass RateMax12.8%Artificial Analysis
              GDP.pdf: All-pass RateNon-reasoning3.8%Artificial Analysis
              GDPval-AA v2.1 LeaderboardMax1600Artificial Analysis
              GDPval-AA v2.1 LeaderboardNon-reasoning1347Artificial Analysis
              Harvey LAB-AA v1.1: Hallucination-Gated All-Pass RateMax1.7%Artificial Analysis
              Humanity's Last ExamMax39.2%Artificial Analysis
              Humanity's Last ExamNon-reasoning10.8%Artificial Analysis
              ITBench-AAMax46.9%Artificial Analysis
              LMArena Agent ArenaMax4.0LMArena
              MaxxBenchMax55.6%unLAP
              MLCR-AAMax23.9%Artificial Analysis
              MMMU-ProMax77.0%Artificial Analysis
              MMMU-ProNon-reasoning65.6%Artificial Analysis
              Multi-step SWEMax6.5%Klavis AI
              SciCodeMax51.9%Artificial Analysis
              SciCodeNon-reasoning35.5%Artificial Analysis
              Terminal-Bench v4.0Max26.8%Artificial Analysis
              Terminal-Bench v4.0Non-reasoning5.6%Artificial Analysis
              Terminal-Bench-Science 0.1Max9.0%Artificial Analysis
              Terminal-Bench-Science 0.1Non-reasoning0.0%Artificial Analysis
              Benchmark scores & sources

              Original results, evaluation harnesses, and evidence behind this model.

              BenchmarkBucketScoreHarnessEvidenceSource-recorded date
              ARC-AGI-2Hard reasoning72.9%ARC Prize verified

              Effort: Not specified

              contributes to capability
              official board2026-09-10
              Artificial Analysis Cyber IndexSupporting evidence40.81131888823 Artificial Analysis Stirrup · Cyber Index v1.0 · max

              Effort: Max

              Cyber Index source settings

              Artificial Analysis Stirrup, v1.0. Display only. This composite measures defensive source-code tasks. Successful capability scores depend on safety refusals, and refusal rates are reported separately. It does not enter weighted Overall.

              Official Cyber Index board
              official board

              Supporting evidence outside the reviewed capability core

              2026-11-18
              Bug Hunt BenchSupporting evidence20.67%Bug Hunt Bench · max

              Effort: Not specified

              official board

              Supporting evidence outside the reviewed capability core

              2026-09-15
              FrontierCS 2Supporting evidence12.5%DeepSeek Harness

              Effort: Not specified

              official board

              Supporting evidence outside the reviewed capability core

              2026-11-20
              LMArena Agent ArenaSupporting evidence2.74 LMArena Agent Arena · max

              Effort: Not specified

              official board

              Supporting evidence outside the reviewed capability core

              2026-10-16
              Multi-step SWESupporting evidence6.5%Claude Code

              Effort: Not specified

              official board

              Supporting evidence outside the reviewed capability core

              2026-11-06
              DeepSWE v1.1Agentic————
              GDPval-AAAgentic————
              GPQA DiamondHard reasoning————
              Humanity's Last ExamHard reasoning————
              LiveCodeBenchCoding————
              LMArena Text ArenaHuman pref————
              MMLU-ProKnowledge————
              OSWorld-VerifiedAgentic————
              SWE-bench ProAgentic————
              SWE-bench VerifiedAgentic————
              Terminal-Bench 2.1Agentic————