sightings

DeepSeek Harness

github.comgithub.com
establishedexternal

Site: github.com

Also seen as: 20 Questions Bench · AI Agent Web Constructor · AI City Resident Agent · AstrBot Test · Buzz POC check · ClipFactory Video Scoring · CoreThink Neurosymbolic Reasoning Engine · Court Rules Monitor v2 · DeobfuscatorAI · Firefox AI Evals · HashSQL solver-bound simulation · Hinode Benchmark Studio · IntelliProcure-NLP · Knowledge Graph System · LLM-FX Jev IFO (llmfx-7d5fa55f20) · LoSoNA eval harness · MindTrial · OL · ONSET brain corpus · ONSET round three, listing model · OPC-Werkstatt · One API · OpenJev Playground · OpenRouter Heavy Model Testing · OrgSim · Paper 2 Agentic M&A Target Recovery · Phills Agent · RP-Bench · RealityBench-Capture · Reductor · SciCode Formats · Scrape Master LLM Bench · Sentry MCP · Service AI Multimodal Gateway · Siege ORLoad · SimWorld SceneBenchmark · SkyrimNet · StepCode · SyntaxMesh · TaskWeaver-UI · Thesis claim check · Tolokaforge Evaluation · TranslateBookWithLLM · VIBeS LLM alignment benchmark · WGO-Bench reproduction · WIENSBENCH · agent-monitor-detection · clara jev triage · claude-mem · codex-fleet conductor · dash-ocr-pipeline structured-stage12 · draco-cascade-bench · experiential · fut7-highlights bench · gmbuster email digest test · gmbuster email summary · hebrew-agentic-bench · ifeval baseline · jev-mcp · jev-mcp (ASUS) · jev-mcp (ip-172-26-8-20) · nl-snackpass-ams · onet-crosswalk pilot-01 · pareto-autoresearch · routatic-proxy · rustllm · session-kb · sewer-vlm openrouter prediction · sn38-leak-sft-llm-draft · tbench-openrouter · uxonews extraction bake-off · uxonews ingest · vadbias-annotation · voice-control round three, the words model · wenzhang-gen

Sightings observed DeepSeek Harness with 79 models in OpenRouter-published model-page evidence. The app was first observed by Sightings on ; relationship dates record when Sightings first saw each pairing, not when usage began.

Global rank
#5
public app rankings
Tokens · yday
351.1B
closed UTC day
Models observed
79
model pages expose top 5
First observed
2025-01-01
by Sightings

What it is

Join the world's most widely adopted, AI-powered developer platform where millions of developers, businesses, and the largest open source community build software that advances humanity.

↗ github.com

Models observed with this app

Early adopter — relationship first observed within 30 days of the model's OpenRouter listing. First-observed dates are when Sightings first saw the pairing, not the start of an app's model usage.

ModelTokens · latestFirst observed
OpenAI: GPT-6 Astraopenai/gpt-6-astraearly adopter709B
StepFun: Step 5 Previewstepfun/step-5-previewearly adopter695B
minimax/minimax-m3.1-flash-20261019:freeminimax/minimax-m3.1-flash-20261019:free495B
minimax/minimax-m3.1-flash:freeminimax/minimax-m3.1-flash:free493B
Z.ai: GLM 5.3 Flashz-ai/glm-5.3-flashearly adopter254B
minimax/minimax-m3-20260531:freeminimax/minimax-m3-20260531:free229B
DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash179B
OpenAI: GPT-5.6 Lunaopenai/gpt-5.6-luna147B
OpenAI: GPT-6.1 Solopenai/gpt-6.1-solearly adopter140B
stealth/space-bunny-alphastealth/space-bunny-alpha128B
nex-agi/nex-n2.5-pro-20260907:freenex-agi/nex-n2.5-pro-20260907:free87.3B
nex-agi/nex-n2.5-pro:freenex-agi/nex-n2.5-pro:free87.3B
DeepSeek: DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813early adopter81.1B
Qwen: Qwen3.8 27Bqwen/qwen3.8-27bearly adopter63.5B
Qwen: Qwen3.7 Flashqwen/qwen3.7-flash59B
DeepSeek: DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-expearly adopter50.6B
thinkingmachines/inkling-20260715:freethinkingmachines/inkling-20260715:free49.5B
Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite33B
Xiaomi: MiMo-V2.5xiaomi/mimo-v2.530.5B
Xiaomi: MiMo-V2.6-Proxiaomi/mimo-v2.6-proearly adopter26.6B
typesafe/jev-1.13typesafe/jev-1.1324.1B
Qwen: Qwen3.8 Flashqwen/qwen3.8-flashearly adopter21B
Google: Gemma 4 31Bgoogle/gemma-4-31b-it18.4B
Inception: Mercury 3inception/mercury-3early adopter14.1B
Mistral: Mistral Nemomistralai/mistral-nemo12.8B
OpenAI: gpt-oss-120bopenai/gpt-oss-120b11.5B
Meta: Muse Wondermeta/muse-wonderearly adopter10.1B
Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it9.24B
Anthropic: Claude Haiku 5.5anthropic/claude-haiku-5.5early adopter8.14B
qwen/qwen3.8-27b-20260814:freeqwen/qwen3.8-27b-20260814:free8.05B
Tencent: Hy4 previewtencent/hy4-previewearly adopter4.53B
Thinking Machines: Inkling Small (free)thinkingmachines/inkling-small:freeearly adopter4.1B
Qwen: Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b4.09B
Z.ai: GLM 5.3 FlashXz-ai/glm-5.3-flashxearly adopter4.02B
typesafe/jev-1.14typesafe/jev-1.142.62B
Tencent: Hy-MT2-30B-A3Btencent/hy-mt2-30b-a3bearly adopter2.32B
inclusionai/ling-3.0-flash-fin-20260827:freeinclusionai/ling-3.0-flash-fin-20260827:free2.3B
inclusionai/ling-3.0-flash-fin:freeinclusionai/ling-3.0-flash-fin:free2.3B
Tencent: Hy-MT2-1.8Btencent/hy-mt2-1.8bearly adopter2.24B
nex-agi/nex-n2.5-mini:freenex-agi/nex-n2.5-mini:free1.55B
inception/mercury-2.5-previewinception/mercury-2.5-preview1.54B
Anthropic: Claude Fable 5.1anthropic/claude-fable-5.1early adopter1.37B
OpenAI: GPT-6 Luna Proopenai/gpt-6-luna-proearly adopter1.31B
Qwen: Qwen3.8 Omni Flashqwen/qwen3.8-omni-flashearly adopter1.28B
Tencent: Hy-MT2-7Btencent/hy-mt2-7bearly adopter1.26B
inclusionAI: Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vlearly adopter1.13B
openai/gpt-6-luna-decisionsopenai/gpt-6-luna-decisions968M
IBM: Granite 4.2 8Bibm-granite/granite-4.2-8bearly adopter964M
Inception: Mercury 2.5inception/mercury-2.5early adopter951M
LiquidAI: LFM2.5-2.6B (free)liquid/lfm-2.5-2.6b:freeearly adopter808M
XingChen: Xing4.0 29B A4B (free)xingchen-agi/xing4.0-29b-a4b:freeearly adopter598M
Z.ai: GLM 5.3 Primez-ai/glm-5.3-primeearly adopter583M
inclusionai/ling-3.0-flash-vl:freeinclusionai/ling-3.0-flash-vl:free496M
Qwen: Qwen3.8 Max Primeqwen/qwen3.8-max-primeearly adopter451M
Meta: Muse Glimmer 30Bmeta/muse-glimmer-30bearly adopter299M
Nex AGI: Nex-N2.5-Mininex-agi/nex-n2.5-miniearly adopter287M
LiquidAI: LFM2.5-24B-A2Bliquid/lfm-2.5-24b-a2bearly adopter180M
Reflection: Beam 1.0 501B A23Breflection/beam-1.0-501b-a23bearly adopter138M
Nex AGI: Nex-N2.5-Pronex-agi/nex-n2.5-proearly adopter115M
ScaleDown: Summarizescaledown/summarizeearly adopter59M
inclusionAI: Ling 3.1 Flashinclusionai/ling-3.1-flashearly adopter50.1M
Perceptron: Perceptron Mk1.5perceptron/perceptron-mk1.5early adopter33.9M
Elorian: Glimpseelorian/glimpseearly adopter26M
ByteDance Seed: Seed-2.0-Codebytedance-seed/seed-2.0-codeearly adopter21.6M
Sakana: Fugu Ultra v2sakana/fugu-ultra-v2early adopter16.6M
NVIDIA: Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vlearly adopter13.1M
Pareto 26.9unbiased/pareto-26.9early adopter9.71M
ScaleDown: Extractscaledown/extractearly adopter7.4M
Inference.net: Schematron V2 Turboinference-net/schematron-v2-turboearly adopter6.24M
inclusionai/ling-3.0-flash-fininclusionai/ling-3.0-flash-fin4.81M
Cohere: Command A+cohere/command-a-plusearly adopter4.42M
Google: Nano Banana 2.1google/gemini-nano-banana-2.1early adopter2.97M
Inference.net: Schematron V2 Smallinference-net/schematron-v2-smallearly adopter2.44M
Upstage: Solar Mini 4upstage/solar-mini4early adopter1.53M
AionLabs: Aion 3.5aion-labs/aion-3.5early adopter1.24M
Moondream: Moondream 3.1moondream/moondream3.1-9b-a2bearly adopter363K
apodex/apodex-1.1-mini:freeapodex/apodex-1.1-mini:free335K
DeepSeek: DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashearly adopter2.86T
DeepSeek: DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017early adopter1.49T