Graph explorer Model
Benchmark graph around deepseek-v4-flash-0420-non-reasoning
Benchmarks and the models evaluated on them — two hops. Click a node to inspect it, double-click to expand, drag to pan, wheel to zoom.
145 nodes · 606 edges
145 nodes · 606 edges
100% · drag to pan · wheel or pinch to zoom · double-click a node to expand
Every node, as a list (145)
- ModelGranite 4.2 8BIBM
- ModelQwen3 Coder NextQwen
- ModelKimi K2.5Moonshot AI
- ModelGPT-5.1-Codex MiniOpenAI
- ModelQwen3 VL 235B A22B InstructQwen
- ModelQwen3 Coder 30B A3B InstructQwen
- ModelReka Flash 3rekaai
- Modelgpt-3.5-turboOpenAI
- ModelGrok 4.6xAI
- ModelMuse Spark 1.1Meta AI
- ModelZ.ai GLM 5.2Z.ai (Zhipu AI)
- ModelClaude Fable 5Anthropic
- ModelMistral Medium 3.5Mistral AI
- ModelGemma 4 31BGoogle
- ModelGrok 4.20xAI
- Modelgpt-5.4-nanoOpenAI
- Modelllama-2-chat-7bMeta AI
- Modeldeepseek-v4-flashDeepSeek
- Modelllama-65bMeta AI
- Modelgemini-2.0-flash-expGoogle
- ModelKAT-Coder-Pro V2Kwaipilot
- Modellfm2-24b-a2bLiquid AI
- ModelClaude Haiku 4.5Anthropic
- ModelClaude Opus 4.1Anthropic
- Modelquasar-438bMultiverse Computing
- Modelo3-proOpenAI
- ModelClaude Sonnet 4Anthropic
- ModelMistral Medium 3Mistral AI
- Modelolmo-2-7bAllen Institute for AI
- Modelo1-proOpenAI
- Modeljamba-reasoning-3bAI21 Labs
- ModelMiniMax M2MiniMax
- Modeltulu3-405bAllen Institute for AI
- ModelQwen3-VL-4B-InstructQwen
- Modelagnes-2-5-pro-betaSapiens AI
- ModelQwen2.5 72B InstructQwen
- Modelgpt-4o-miniOpenAI
- BenchmarkGPQA Diamond
- ModelQwen3.6 PlusQwen
- Modelgpt-4oOpenAI
- Modelgpt-oss-120bOpenAI
- ModelGPT-4o (2024-05-13)OpenAI
- ModelPhi 4Microsoft
- Modelopenchat-35OpenChat
- Modelmuse-sparkMeta AI
- Modelring-2-6-1tinclusionAI
- ModelGemini 3.7 FlashGoogle
- Modelgpt-5-chatgptOpenAI
- BenchmarkHumanity's Last Exam
- Modeljamba-1-6-miniAI21 Labs
- ModelMistral Small 3Mistral AI
- Modelnova-premierAmazon Web Services
- ModelQwen2.5-Coder-7BQwen
- Modelgpt-5-5-instant-05-26OpenAI
- ModelLing 3.0 FlashinclusionAI
- ModelLFM2.5-8B-A1BLiquid AI
- ModelLFM2.5-2.6B (free)Liquid AI
- BenchmarkTerminal-Bench
- Modelgemini-2-0-flash-thinking-exp-1219Google
- ModelDeepSeek-R1-Distill-Qwen-32BDeepSeek
- Modelmi-dm-k-2-5-pro-dec28Korea Telecom
- Modelphi-3-miniMicrosoft
- ModelPixtral LargeMistral AI
- Modelk2-v2MBZUAI Institute of Foundation Models
- Modelclaude-2Anthropic
- Modelgranite-4-0-h-nano-1bIBM
- BenchmarkArtificial Analysis Intelligence Index
- Modelsolar-miniUpstage
- ModelGemini 2.0 FlashGoogle
- Modelgrok-3-mini-reasoningSpaceXAI
- Modelcogito-v2-1-reasoningDeep Cogito
- Modelgranite-4.1-30bIBM
- Modelminicpm5-1bOpenBMB
- Modelqwen1.5-110b-chatAlibaba Group
- BenchmarkIFBench
- Modelgemma-3-1bGoogle
- ModelQwQ-32BAlibaba Group
- Modelgemini-3-proGoogle
- Modelllama-3-1-nemotron-ultra-253b-v1-reasoningNVIDIA
- Modeldeephermes-3-llama-3-1-8b-previewNous Research
- Modelllama-3-1-nemotron-nano-4b-reasoningNVIDIA
- Modeldeephermes-3-mistral-24b-previewNous Research
- ModelDevstral Small 2Mistral AI
- ModelGLM 5.3Z.ai (Zhipu AI)
- ModelDevstral Small 1.0Mistral AI
- Modelqwen3-max-thinking-previewAlibaba Group
- ModelMixtral 8x22BMistral AI
- Modelolmo-3-32b-thinkAllen Institute for AI
- Benchmarkτ²-bench
- Modelfalcon-h1r-7bTII UAE
- Modeldeepseek-coder-v2-liteDeepSeek
- Modelgemini-2-0-pro-experimental-02-05Google
- Modelqwen-chat-14bAlibaba Group
- Modelgpt-5-5-instant-06-26OpenAI
- Modeldiffusiongemma-26b-a4bGoogle
- Modelg9v3-39a5bAI9Stars
- Modelqwen3-32b-instructAlibaba Group
- ModelKimi K2 ThinkingMoonshot AI
- Modelgemma-3n-e4b-preview-0520Google
- Modeldeepseek-v2-5DeepSeek
- ModelGemini 3.1 Pro PreviewGoogle
- Modelk2-horizon-375b-a23bMBZUAI Institute of Foundation Models
- Modelqwen-2-5-maxAlibaba Group
- ModelSolar Pro 3Upstage
- ModelTrinity Large ThinkingArcee AI
- Modelo1-miniOpenAI
- Modeljamba-1-7-miniAI21 Labs
- Modeljamba-1-5-largeAI21 Labs
- Modelgpt-4o-chatgptOpenAI
- Modelarctic-instructSnowflake
- Modelclaude-3-sonnetAnthropic
- Modeldeepseek-r1-distill-qwen-14bDeepSeek
- Modelmotif-3Motif Technologies
- Modelmolmo-7b-dAllen Institute for AI
- ModelLlama 4 ScoutMeta AI
- Modelstep-3-vl-10bStepFun
- Modelclaude-35-sonnet-june-24Anthropic
- Modelgemini-1-5-flash-may-2024Google
- Modelapriel-v1-5-15b-thinkerServiceNow
- Modelcommand-r-03-2024Cohere
- Modeldevstral-mediumMistral AI
- Modelllama-3-instruct-70bMeta AI
- Modelreka-flashrekaai
- Modelgemma-3n-e2bGoogle
- ModelQwen 3.7 PlusQwen
- Modeldeepseek-r1DeepSeek
- Modelgemma-3n-e4bGoogle
- Modelapriel-v1-6-15b-thinkerServiceNow
- Modelgranite-4-0-h-350mIBM
- Modelernie-5-0-thinking-previewBaidu
- Modelk-exaoneLG AI Research
- ModelDeepSeek-V4.1-FlashDeepSeek
- Modelclaude-instantAnthropic
- Modeldeepseek-v4-proDeepSeek
- Modelgranite-4.1-8bIBM
- ModelLlama-3.2-1BMeta AI
- ModelQwen3.6 Max PreviewQwen
- ModelGemini 3.1 Flash-Lite PreviewGoogle
- ModelCommand ACohere
- Modelmimo-v2-omni-0327Xiaomi
- Modelgrok-3SpaceXAI
- Modelkat-coder-pro-v1KwaiKAT
- Modelmidm-250-pro-rsnsftKorea Telecom
- Modelernie-4-5-300b-a47bBaidu
- Modeldeepseek-v4-flash-0420-non-reasoningDeepSeek
Direct relations of deepseek-v4-flash-0420-non-reasoning, as a list
- Evaluated on 6
- BenchmarkGPQA DiamondBenchmarkArtificial Analysis Intelligence IndexBenchmarkHumanity's Last ExamBenchmarkIFBenchBenchmarkτ²-benchBenchmarkTerminal-Bench