Skip to content

DeepSeek · Chat

DeepSeek V4.1 Flash

DeepSeek 🇨🇳ChatDeepSeek familyOne of its sources says the weights aren't publicly available.The maker currently plans to deprecate it within the next 180 days (15 Dec 2026). Plans can change.

DeepSeek released two versions of V4.1 Flash: 10 Sep 2026 and 17 Oct 2026. The listings here couldn't be matched to one of them.

From Baseten's listing:
A 552B-parameter mixture-of-experts model with native vision and 1M-token context, activating just 8B parameters during prefill and 16B during decode for efficient reasoning, coding, and agentic workloads.
llminfo IQ
137.7
Market median price
$0.50 blended / 1M
Max context
1.1M
Listings
252

Evidence and sources

Model architecture, as its sources state it llminfo IQ 137.7, ranked among chat models. From 179 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 124.7, 95% interval 109–140. From 20 benchmark families across 6 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedGood value (68.1). Cheaper per task than its benchmark results predict. From 50 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsChatty (60 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. By effort: default 60 · high 62.Median 67,313 output tokens per task at default effort.How the Yap score worksMaker HQ: CN (according to DeepSeek's own website)
All rankings: #11 on NanoGPT recentlySources: Arcee AI data, Mancer data, ModelRunner.ai data, sference data, LiteLLM data, Baseten dataPrimary data from Arcee AI from Mancer: architecture from ModelRunner.ai: weights availability from sference: primary mode from LiteLLM: deprecation date from Baseten: description
Tags from its sources:instructtoolsreasoningvisionopen-sourcemultimodalcodingagenticlong-contextmoe

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Trade-offs

Deprecation scheduled

The maker plans to deprecate it on 15 Dec 2026, within the next 180 days.

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 8 maker's prices; 2 market median prices.

Input & output

as stated by the model's providers
Text
Images
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt caching

Listings

 Opencodedeepseek-v4.1-flash-free · freeSource: OpenCode Zen dataNot published by the provider$0.00$0.00
 Refuselessdeepseek-v4.1-flash-fast · fastSource: Models.dev data1M$0.01cache read $0.002$0.08
 Engydeepseek-v4.1-flashSource: Models.dev data1M$0.03cache read $0.006$0.12
 NanoGPTdeepseek/deepseek-v4.1-flashSources: Models.dev data, NanoGPT1M$0.0387cache read $0.0089$0.40
 Ezkielynadeepseek-v4.1-flashSource: Models.dev data1M$0.04cache read $0.0054$0.16
 Kilodeepseek/deepseek-v4.1-flashSources: Kilo AI Gateway data, Models.dev data1M$0.0498cache read $0.001$0.1992
 OpenRouterdeepseek/deepseek-v4.1-flashSource: Models.dev data1M$0.0498cache read $0.001$0.1992
 Hugging FaceInference by Open Inferencedeepseek-ai/DeepSeek-V4.1-FlashSource: Hugging Face Inference Providers data1M$0.05$0.75
 Openinferencedeepseek-ai/DeepSeek-V4.1-Flash · fp4Source: OpenInference data1M$0.05cache read $0.002$0.75
 Korouterdeepseek-v4.1-flashSource: Models.dev data1M$0.066cache read $0.0013$0.264

20 listings without a price are hidden.

Included in plans

CheapestInference Core PoolcheapestinferenceSubscription$22/moPlan page
Umans Code ProumansSubscription$20/moslows down past the allowancePlan page
Umans Code MaxumansSubscription$50/moslows down past the allowancePlan page

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Agentic

Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
官方 scaffold / Pass@1
GAIA4 results
Source: GAIA Leaderboard data · Oct 2026
Difficulty level
Difficulty not reported
Source: OpenRouter benchmark exports
10 Sep 2026 version · 90-day results
Across 40 providers lowest 64.6% median 73.4% highest 76.3%OpenRouter's automatic routing 75.1%
Show results from 40 providers and OpenRouter's automatic routingHide results from 40 providers and OpenRouter's automatic routing
  • Crusoe
  • DekaLLM
  • NextBit
  • DigitalOcean
  • Alibaba
  • Novita
  • Baidu
  • OpenRouter's automatic routing
  • SiliconFlow
  • DeepInfra
  • Decart
  • StreamLake
  • Sail Research
  • GMICloud
  • Phala
  • AtlasCloud
  • River
  • InferenceNet
  • Morph
  • Makora
  • Fireworks
  • Mancer 2
  • Modal
  • CoreWeave
  • Wafer
  • Ionstream
  • Nebius
  • Reka
  • Together
  • ModelRun
  • PrimeIntellect
  • Relace
  • BaseTen
  • Venice
  • Io Net
  • Parasail
  • Cloudflare
  • OpenInference
  • Cohere
  • Google
  • Krea
Terminal-Bench 2.14 related benchmarks · 17 results
Terminal-Bench 2.1
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
max effort · temp 1.0 · top_p .95 · 1M · max_steps 500 · N=3 · no network
DeepSeek V4.1 launch chart · settings unspecified
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Terminal-Bench 3.0
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek Harness / max effort
DeepSeek V4.1 launch chart · settings unspecified
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Terminal-Bench 4.0
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek Harness / max effort
DeepSeek V4.1 launch chart · settings unspecified
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Source: WeirdML v3 data
config: deepseek-v4.1-flash-novita-high-codex, agent: codex_cli, harness: codex_cli@0.156.0, effort: high
config: deepseek-v4.1-flash-novita-high-opencode, agent: opencode, harness: opencode@1.18.30, effort: high

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond44 results
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
Pass@1 / max effort
Source: OpenRouter benchmark exports
10 Sep 2026 version · 90-day results
Across 40 providers lowest 72.3% median 88.5% highest 90.9%OpenRouter's automatic routing 89.1%
Show results from 40 providers and OpenRouter's automatic routingHide results from 40 providers and OpenRouter's automatic routing
  • NextBit
  • Alibaba
  • Baidu
  • Mancer 2
  • SiliconFlow
  • StreamLake
  • DeepInfra
  • Novita
  • DigitalOcean
  • GMICloud
  • AtlasCloud
  • Phala
  • ModelRun
  • Morph
  • InferenceNet
  • Wafer
  • OpenRouter's automatic routing
  • Cloudflare
  • Google
  • Sail Research
  • River
  • DekaLLM
  • Crusoe
  • Nebius
  • Venice
  • Reka
  • Together
  • PrimeIntellect
  • Modal
  • Parasail
  • Relace
  • Decart
  • BaseTen
  • Makora
  • Ionstream
  • OpenInference
  • Fireworks
  • Cohere
  • CoreWeave
  • Io Net
  • Krea

Coding

Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
reasoning_effort 100
CyberGym3 results
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
ExploitBenchExploitBench API harness / 5 seeds · Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
NL2RepoSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
SEC-Bench Pro3 results
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Claude Code harness
DeepSeek V4.1 launch chart · settings unspecified
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SkillsBenchLing-3.1-flash official chart · SkillsBench · version, task count, harness, reasoning setting and run count not stated · Reported by Ant inclusionAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ValsSource: Vals AI

Reasoning

Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
官方 scaffold / Pass@1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
BabyVision3 results
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified · with tools
with tools · Claude Code · 512K · pass@1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Chartography3 results
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified · with tools
with tools · Claude Code · 512K · pass@1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Humanity's Last Exam3 related benchmarks · 9 results
Humanity's Last Exam
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Task set · DeepSeek V4.1 launch chart · settings unspecified
Task set · pass@1 · reasoning_effort 100 · temp 1.0 · top_p .95
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
(no tools, text-only)
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
(with tools)
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
ZEROBenchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Multilingual

Bangla LLM BenchSource: Bangla LLM Bench data docs
Benchmark Nusantara7 related benchmarks · 7 results
Show 1 more resultHide 1 result
EKI EstonianSource: Keelemudelite mõõdupuu data docs · Sep 2026

General

Human preference

Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Math

Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
pass@1 · reasoning_effort 100
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Factuality

Other

BlenderWorld15 related benchmarks · 15 results
Art & Animation
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 30 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Architecture & Interiors
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 72 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Characters & Animals
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 25 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Fully satisfied rubric
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 223 tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Image/video-input overall score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 145 image or video reference tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Nature & Landscapes
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Show 9 more resultsHide 9 results
Overall score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 223 tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Procedural & Game Assets
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 10 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Products & Manufacturing
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 28 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Rendering & Simulation
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 17 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Science & Visualization
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 9 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Text-only overall score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 78 text-only tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Vehicles & Machinery
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 11 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Visual-quality dimension score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 223 tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Weighted rubric score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 223 tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
DeepSWE v1.19 results
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
max effort · temp 1.0 · top_p .95 · 1M · max_steps 500 · N=8
DeepSeek V4.1 launch chart · settings unspecified
ExploitGym5 related benchmarks · 14 results
Success Rate
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
on-target exploits
Source: ExploitGym leaderboard data docs
agent: MopMonk Agent, eval: 8h timeout, selected subset, version: v1, focus: agent
agent: MopMonk Agent, eval: 8h timeout, selected subset, version: v1, focus: agent
agent: VARAS-OneMind (智安·宇盾), eval: 6h timeout, version: v1, focus: agent
on-target exploits (kernel)
Source: ExploitGym leaderboard data docs
agent: MopMonk Agent, eval: 8h timeout, selected subset, version: v1, focus: agent
agent: MopMonk Agent, eval: 8h timeout, selected subset, version: v1, focus: agent
agent: VARAS-OneMind (智安·宇盾), eval: 6h timeout, version: v1, focus: agent
on-target exploits (userspace)
Source: ExploitGym leaderboard data docs
agent: MopMonk Agent, eval: 8h timeout, selected subset, version: v1, focus: agent
agent: MopMonk Agent, eval: 8h timeout, selected subset, version: v1, focus: agent
agent: VARAS-OneMind (智安·宇盾), eval: 6h timeout, version: v1, focus: agent
on-target exploits (V8)
Source: ExploitGym leaderboard data docs
agent: MopMonk Agent, eval: 8h timeout, selected subset, version: v1, focus: agent
agent: MopMonk Agent, eval: 8h timeout, selected subset, version: v1, focus: agent
agent: VARAS-OneMind (智安·宇盾), eval: 6h timeout, version: v1, focus: agent
ExplorationBench22 related benchmarks · 22 results
AlienCode · M4 · fixed-probe control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
AlienCode · A4+O · complete rules after exploration
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · complete-rule reference or auxiliary diagnostic
AlienCode · M0 · baseline of Best@3 trajectory
Reported by Fudan University / Tencent Hy / Tsinghua University, Tencent Hy / ExplorationBench authors · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienCode · M4 · Best@3 held-out accuracy
Reported by Fudan University / Tencent Hy / Tsinghua University, Tencent Hy / ExplorationBench authors · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienCode · M4 · direct answering control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
AlienCode · M4 · hindsight-replay control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
Show 16 more resultsHide 16 results
AlienCode · M4 · Mean@3 held-out accuracy
Reported by Fudan University / Tencent Hy / Tsinghua University, Tencent Hy / ExplorationBench authors · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienCode · M4 · without-tool control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
AlienCode · M4 · Worst@3 held-out accuracy
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienCode · O@M0 · complete rules before exploration
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · complete-rule reference or auxiliary diagnostic
AlienCode · Rules correctly reported
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · complete-rule reference or auxiliary diagnostic
AlienLogic · A4+O · complete rules after exploration
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · complete-rule reference or auxiliary diagnostic
AlienLogic · Correct refusal on unprovable tasks
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · complete-rule reference or auxiliary diagnostic
AlienLogic · M0 · baseline of Best@3 trajectory
Reported by Fudan University / Tencent Hy / Tsinghua University, Tencent Hy / ExplorationBench authors · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienLogic · M4 · Best@3 held-out accuracy
Reported by Fudan University / Tencent Hy / Tsinghua University, Tencent Hy / ExplorationBench authors · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienLogic · M4 · direct answering control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
AlienLogic · M4 · fixed-probe control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
AlienLogic · M4 · hindsight-replay control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
AlienLogic · M4 · Mean@3 held-out accuracy
Reported by Fudan University / Tencent Hy / Tsinghua University, Tencent Hy / ExplorationBench authors · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienLogic · M4 · without-tool control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
AlienLogic · M4 · Worst@3 held-out accuracy
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienLogic · O@M0 · complete rules before exploration
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · complete-rule reference or auxiliary diagnostic
NL2Repo-Bench2 results
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified · launch-page table
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
SkillsBench · Vals6 related benchmarks · 6 results
With Skills · Accuracy
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=deepseek/deepseek-v4.1-flash · provider=DeepSeek · reasoning_effort=high · max_output_tokens=384000
With Skills · Mean cost / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=deepseek/deepseek-v4.1-flash · provider=DeepSeek · reasoning_effort=high · max_output_tokens=384000
With Skills · Mean duration / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=deepseek/deepseek-v4.1-flash · provider=DeepSeek · reasoning_effort=high · max_output_tokens=384000
Without Skills · Accuracy
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=deepseek/deepseek-v4.1-flash · provider=DeepSeek · reasoning_effort=high · max_output_tokens=384000
Without Skills · Mean cost / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=deepseek/deepseek-v4.1-flash · provider=DeepSeek · reasoning_effort=high · max_output_tokens=384000
Without Skills · Mean duration / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=deepseek/deepseek-v4.1-flash · provider=DeepSeek · reasoning_effort=high · max_output_tokens=384000
Vals15 related benchmarks · 17 results
Show 11 more resultsHide 11 results
Immigration
Source: Vals AI
LegalBench
Source: Vals AI
MedCode
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
MedScribe
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
SAGE
Source: Vals AI
SRE Bench
Source: Vals AI
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified · with tools
with tools · Claude Code · 512K · pass@5

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats · Hugging Face official benchmark leaderboards; licence varies by benchmark · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · LMArena, CC BY 4.0 (licence) · Bangla LLM Bench, Md Deluair Hossen. Source tasks: Hendrycks et al. 2021 (MMLU), OpenAI MMMLU, Bandarkar et al. 2024 (Belebele), Shi et al. 2023 (MGSM), Nahin et al. 2025 (TituLLMs). Public numeric community results; results licence not separately stated. · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · Benchmark Nusantara, ibahasa (M. Khoirul Huda), doi:10.5281/zenodo.21970463. Test results CC BY 4.0, attribution to ibahasa; aggregate results CSV only. (licence) · BullshitBench by Peter Gostev, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · CyberGym leaderboard (Wang, Shi, He, Cai, Zhang, Song; UC Berkeley), ICLR 2026. Results evaluated and submitted by the listed teams. No licence is stated for the result data; the repository's Apache-2.0 licence covers its code only. · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · ExploitGym leaderboard (Wang et al., UC Berkeley), arXiv:2605.11086. No licence is stated for the result data; the repository's Apache-2.0 licence covers its code only, and task data keeps its upstream licences. Literal exploit counts; hidden rows omitted. · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · MineBench, MIT (licence) · SWE-bench-Live (Microsoft and contributors), swe-bench-live.github.io. Resolve rates computed from the published report counts. · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted. · Vectara Hallucination Leaderboard, Apache-2.0 (licence) · WeirdML v3 by Håvard Tveit Ihle (Norwegian Defence Research Establishment). API costs supported by Epoch AI, METR and NDRE.

Also known as: accounts/fireworks/models/deepseek-v4p1-flash, alibaba/deepseek-v4.1-flash, alibaba/deepseek-v4.1-flash-latest, azure_ai/deepseek-v4.1-flash, azure_ai/fw-deepseek-v4.1-flash, baseten/deepseek-ai/deepseek-v4.1-flash, baseten/deepseek-ai/deepseek-v4.1-flash-fast, cline-pass/deepseek-v4.1-flash, cloudflare/deepseek-v4.1-flash-latest, databricks/databricks-deepseek-v4-1-flash, deepinfra/deepseek-ai/deepseek-v4.1-flash, deepinfra/deepseek-v4.1-flash, deepinfra/deepseek-v4.1-flash-latest, deepseek v4.1 flash, deepseek-ai/deepseek-v4.1-flash, deepseek-ai/deepseek-v4.1-flash-fast, deepseek-v4-1-flash, deepseek-v4.1-flash-fast, deepseek-v4.1-flash-flex, deepseek-v4.1-flash-free, deepseek-v4.1-flash-max, deepseek-v4.1-flash:fast, deepseek-v4.1-flash@eu, deepseek-v41-flash, deepseek/deepseek-v4.1-flash, deepseek/deepseek-v4.1-flash-fast, deepseek/deepseek-v4.1-flash-latest, deepseek/deepseek-v4.1-flash:batch, deepseek/deepseek-v4.1-flash:thinking, fireworks/deepseek-v4.1-flash, fireworks/deepseek-v4.1-flash-latest, fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash, fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-us, fireworks_ai/deepseek-v4p1-flash, fireworks_ai/deepseek-v4p1-flash-us, flexai/deepseek-v4.1-flash-latest, gmi/deepseek-ai/deepseek-v4.1-flash, modelrunner-ai/deepseek-v4.1-flash, nebius/deepseek-ai/deepseek-v4.1-flash, novita/deepseek-v4.1-flash, novita/deepseek-v4.1-flash-latest, nvidia_nim/deepseek-ai/deepseek-v4.1-flash, opencode_go/deepseek-v4.1-flash, parasail-deepseek-v41-flash, parasail-deepseek-v41-flash-fast, qwen/deepseek-v4.1-flash, runware/deepseek-v4.1-flash, runware/deepseek-v4.1-flash-latest, scaleway/deepseek-v4.1-flash, scx-ai-gp/deepseek-v4.1-flash, scx-ai-gp/deepseek-v4.1-flash-latest, scx-ai/deepseek-v4.1-flash, tee/deepseek-v4.1-flash, tencent/deepseek-v4.1-flash, tencent/deepseek-v4.1-flash-latest, tensorx/deepseek/deepseek-v4.1-flash, together-ai/deepseek-v4.1-flash, together-ai/deepseek-v4.1-flash-latest, together_ai/deepseek-ai/deepseek-v4.1-flash, umans-deepseek-v4.1-flash, vertex_ai/deepseek-ai/deepseek-v4.1-flash-maas, wandb/deepseek-ai/deepseek-v4.1-flash

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works