ModelBench
Model catalog

Models

Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.

Compare Export CSV
12 models
vercel Open weights
Ranked by Humanity's Last Exam
DeepSeek: DeepSeek V4.1 Flash T
Reasoning Tools JSON Open weights 63.9

DeepSeek V4.1 Flash model for reasoning and agentic coding

deepseek/deepseek-v4.1-flash 2026-09-10 1M context $0.02/M input $1/M output
70 providers
Meta: Muse Spark Open T
Reasoning Tools JSON Open weights 61.0

Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.

meta/muse-spark-open 2026-10-15 1.04858M context $1.25/M input $4.25/M output
14 providers
DeepSeek: DeepSeek V4 Pro 0813 T
Reasoning Tools JSON Open weights 60.0

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

deepseek/deepseek-v4-pro-0813 2026-08-13 1M context $0.132/M input $0.396/M output
42 providers
DeepSeek: DeepSeek V4 Pro T
Reasoning Tools JSON Open weights 48.2

Open MoE flagship with million-token context for coding and long agent runs

deepseek/deepseek-v4-pro 2026-04-24 1M context $0.66/M input $1.98/M output
71 providers
StepFun: Step 3.7 Flash T
Reasoning Tools JSON Open weights 47.2

Newer StepFun flash model for faster agents, coding, and multimodal prompts

stepfun/step-3.7-flash 2026-05-29 256K context $0.202/M input $1.211/M output
21 providers
DeepSeek: DeepSeek V4 Flash T
Reasoning Tools JSON Open weights 45.1

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

deepseek/deepseek-v4-flash 2026-04-24 1M context $0.15/M input $0.6/M output
68 providers
DeepSeek: DeepSeek V4.1 Flash 1017 T
Reasoning Tools JSON Open weights 44.0

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

deepseek/deepseek-v4.1-flash-1017 2026-10-17 1M context $0.15/M input $0.6/M output
32 providers
NVIDIA: Nemotron 3 Ultra 550B A55B T
Reasoning Tools Open weights 37.4

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

nvidia/nemotron-3-ultra-550b-a55b 2026-06-04 1M context $0.1/M input $0.1/M output
17 providers
Tencent: Hy3 T
Reasoning Tools Open weights 37.0

Tencent Hy reasoning model for coding, instruction following, and agent tasks

tencent/hy3 2026-07-06 256K context $0.066/M input $0.26/M output
23 providers
Alibaba Qwen: Qwen3.8 Flash Next T
Reasoning Tools JSON Open weights 35.9

Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding

alibaba/qwen3.8-flash-next 2026-08-27 262.144K context $0.1/M input $0.2/M output
6 providers
Alibaba Qwen: Qwen3.8 27B T
Reasoning Tools JSON Open weights 30.8

Dense 27B vision-language model for coding, agent tasks, and image and video understanding

alibaba/qwen3.8-27b 2026-08-14 262.144K context $0.04/M input $1.35/M output
46 providers
NVIDIA: Nemotron 3.5 Lightning 30B A3B T
Reasoning Tools JSON Open weights 11.7

Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads

nvidia/nemotron-3.5-lightning 2026-08-11 262.144K context $0.025/M input $0.12/M output
13 providers