# compare models
Pick two to four open-weights models for a side-by-side view of specifications, rankings, benchmarks, price, and serving performance. The URL updates with your selection so the comparison is shareable.
model
select a model
A.x K2 (a.x-k2) — skt DeepSeek R1 (deepseek-r1) — deepseek-ai DeepSeek R1 0528 (deepseek-r1-0528) — deepseek-ai DeepSeek V3 (deepseek-v3) — deepseek-ai DeepSeek V3.1 (deepseek-v3.1) — deepseek-ai DeepSeek V3.1 Terminus (deepseek-v3.1-terminus) — deepseek-ai DeepSeek V3.2 (deepseek-v3.2) — deepseek-ai DeepSeek V4 Flash (deepseek-v4-flash) — deepseek-ai DeepSeek V4 Flash 0731 (deepseek-v4-flash-0731) — deepseek-ai DeepSeek V4 Pro (deepseek-v4-pro) — deepseek-ai DeepSWE Preview (deepswe-preview) — agentica-org Devstral 2 (2512) (devstral-2-2512) — mistralai Devstral Small 2507 (devstral-small-2507) — mistralai Devstral Small 2512 (devstral-small-2512) — mistralai G9v3 39a5b (g9v3-39a5b) — ai9stars G9v3 3B (g9v3-3b) — ai9stars Gemma 2 9B It (gemma-2-9b-it) — google Gemma 3 12B (gemma-3-12b-it) — google Gemma 3 27B (gemma-3-27b-it) — google Gemma 3n E2b It (gemma-3n-e2b-it) — google Gemma 3n E4b (gemma-3n-e4b) — google Gemma 4 12B (gemma-4-12b-it) — google Gemma 4 26B A4B (gemma-4-26b-a4b-it) — google Gemma 4 31B (gemma-4-31b-it) — google GigaChat 3.5 432B A28B (gigachat3.5-432b-a28b) — ai-sage GLM-4.5 (glm-4.5) — zai-org GLM-4.5 Air (glm-4.5-air) — zai-org GLM-4.6 (glm-4.6) — zai-org GLM-4.6V (glm-4.6v) — zai-org GLM-4.7 (glm-4.7) — zai-org GLM-4.7 Flash (glm-4.7-flash) — zai-org GLM-5 (glm-5) — zai-org GLM-5.1 (glm-5.1) — zai-org GLM-5.2 (glm-5.2) — zai-org GPT-OSS 120B (gpt-oss-120b) — openai GPT-OSS 20B (gpt-oss-20b) — openai Granite 3.3 8B Instruct (granite-3.3-8b-instruct) — ibm-granite Granite 4.0 Micro (granite-4.0-h-micro) — ibm-granite Granite 4.1 8B (granite-4.1-8b) — ibm-granite Granite 4.2 30B (granite-4.2-30b) — ibm-granite Granite 4.2 3B (granite-4.2-3b) — ibm-granite Hy3 (hy3) — tencent Hy4 preview (hy4-preview) — tencent Inkling (inkling) — thinkingmachines K2 Horizon 375B A23B (k2-horizon-375b-a23b) — IFM K2 Think V2 (k2-think-v2) — IFM K2 V2 (k2-v2) — IFM Kimi K2 Instruct 0905 (kimi-k2-0905) — moonshotai Kimi K2 Instruct (kimi-k2-instruct) — moonshotai Kimi K2 Thinking (kimi-k2-thinking) — moonshotai Kimi K2.5 (kimi-k2.5) — moonshotai Kimi K2.6 (kimi-k2.6) — moonshotai Kimi K2.7 Code (kimi-k2.7-code) — moonshotai Kimi K3 (kimi-k3) — moonshotai Laguna M.1 (laguna-m.1) — poolside Laguna S 2.1 (laguna-s-2.1) — poolside Laguna Xs.2 (laguna-xs.2) — poolside Leanstral 1.5 119B A6B (leanstral-1.5-119b-a6b) — mistralai Ling-1T (ling-1t) — inclusionai Ling-2.6-1T (ling-2.6-1t) — inclusionai Ling-2.6-flash (ling-2.6-flash) — inclusionai Ling 3.0 Flash Fin (ling-3.0-flash-fin) — inclusionai Llama 3.1 405B Instruct (llama-3.1-405b-instruct) — meta-llama Llama 3.1 Nemotron Nano 8B V1 (llama-3.1-nemotron-nano-8b-v1) — nvidia Llama 3.3 70B Instruct (llama-3.3-70b-instruct) — meta-llama Llama 4 Maverick (llama-4-maverick) — meta-llama Llama 4 Scout (llama-4-scout) — meta-llama LongCat 2.0 (longcat-2.0) — meituan-longcat Magistral Small 2506 (magistral-small-2506) — mistralai MiMo-V2.5 (mimo-v2.5) — xiaomi MiMo-V2.5-Pro (mimo-v2.5-pro) — xiaomi Minicpm Sala (minicpm-sala) — openbmb MiniCPM5 1B (minicpm5-1b) — openbmb MiniMax M1 (minimax-m1) — minimax MiniMax M2 (minimax-m2) — minimax MiniMax M2.1 (minimax-m2.1) — minimax MiniMax M2.5 (minimax-m2.5) — minimax MiniMax M2.7 (minimax-m2.7) — minimax MiniMax M3 (minimax-m3) — minimax Mistral Large 2411 (mistral-large-2411) — mistralai Mistral Large 3 (mistral-large-3) — mistralai Mistral Small 3.2 24B (mistral-small-3.2-24b) — mistralai Molmo2 8B (molmo2-8b) — allenai Motif 3 (motif-3) — Motif-Technologies Muse Glimmer 30B (muse-glimmer-30b) — meta-models Nemotron 3 Nano 30B A3B (nemotron-3-nano-30b-a3b) — nvidia Nemotron Cascade 2 30B A3B (nemotron-cascade-2-30b-a3b) — nvidia Nex-N2-Mini (nex-n2-mini) — nex-agi Nex-N2-Pro (nex-n2-pro) — nex-agi Nvidia Nemotron Nano 9B V2 (nvidia-nemotron-nano-9b-v2) — nvidia OLMo 2 32B Instruct (olmo-2-32b-instruct) — allenai OLMo 3 32B (olmo-3-32b) — allenai Olmo 3 7B Think (olmo-3-7b-think) — allenai Ornith 1.0 35B (ornith-1.0-35b) — deepreinforce-ai Ornith 1.0 397B (ornith-1.0-397b) — deepreinforce-ai Ornith 1.0 9B (ornith-1.0-9b) — deepreinforce-ai Phi 3.5 Mini Instruct (phi-3.5-mini-instruct) — microsoft Phi 4 (phi-4) — microsoft Phi 4 Multimodal Instruct (phi-4-multimodal-instruct) — microsoft Phi 4 Reasoning Plus (phi-4-reasoning-plus) — microsoft Qwen AgentWorld 35B A3B (qwen-agentworld-35b-a3b) — qwen Qwen2.5 72B Instruct (qwen2.5-72b-instruct) — qwen Qwen2.5 Coder 32B (qwen2.5-coder-32b) — qwen Qwen2.5 Omni 7B (qwen2.5-omni-7b) — qwen Qwen2.5-VL-72B-Instruct (qwen2.5-vl-72b-instruct) — qwen Qwen3 14B (qwen3-14b) — qwen Qwen3 235B A22B (qwen3-235b-a22b) — qwen Qwen3 235B A22B Instruct 2507 (qwen3-235b-a22b-instruct-2507) — qwen Qwen3 30B A3B (qwen3-30b-a3b) — qwen Qwen3 32B (qwen3-32b) — qwen Qwen3 Coder 30B A3B (qwen3-coder-30b-a3b) — qwen Qwen3 Coder 480B A35B (qwen3-coder-480b-a35b) — qwen Qwen3 Coder Next (qwen3-coder-next) — qwen Qwen3-Next-80B-A3B-Thinking (qwen3-next-80b-a3b-thinking) — qwen Qwen3-VL-235B-A22B-Instruct (qwen3-vl-235b-a22b-instruct) — qwen Qwen3-VL-235B-A22B-Thinking (qwen3-vl-235b-a22b-thinking) — qwen Qwen3-VL-30B-A3B-Instruct (qwen3-vl-30b-a3b-instruct) — qwen Qwen3-VL-30B-A3B-Thinking (qwen3-vl-30b-a3b-thinking) — qwen Qwen3-VL-32B-Instruct (qwen3-vl-32b-instruct) — qwen Qwen3-VL-4B-Instruct (qwen3-vl-4b-instruct) — qwen Qwen3-VL-8B-Instruct (qwen3-vl-8b-instruct) — qwen Qwen3-VL-8B-Thinking (qwen3-vl-8b-thinking) — qwen Qwen3.5 122B A10B (qwen3.5-122b-a10b) — qwen Qwen3.5-27B (qwen3.5-27b) — qwen Qwen3.5-35B-A3B (qwen3.5-35b-a3b) — qwen Qwen3.5 397B A17B (qwen3.5-397b-a17b) — qwen Qwen3.5 9B (qwen3.5-9b) — qwen Qwen3.6 27B (qwen3.6-27b) — qwen Qwen3.6 35B A3B (qwen3.6-35b-a3b) — qwen Qwen3.8 2.4T A95B (qwen3.8-2.4t-a95b) — qwen Qwen3.8 Flash Next (qwen3.8-flash-next) — qwen QwQ 32B (qwq-32b) — qwen Ring-2.6-1T (ring-2.6-1t) — inclusionai Solar Open 100B (solar-open-100b) — upstage Solar Open2 250B (solar-open2-250b) — upstage Trinity Large Thinking (trinity-large-thinking) — arcee-ai
Choose at least two models.
Model comparison requires JavaScript because it loads the selected records from the public dataset.