ModelBench
Model catalog

Models

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

Compare Export CSV
7 models
nano-gpt Open weights
Ranked by SWE-Bench Multilingual
Reflection: Beam 1.0 501B A23B T
Reasoning Tools Open weights 78.3

Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows

reflection/beam-1.0-501b-a23b 2026-10-05 1.04858M context $0.24/M input $0.98/M output
9 providers
DeepSeek: DeepSeek V4 Pro T
Reasoning Tools JSON Open weights 76.2

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
Tencent: Hy3 T
Reasoning Tools Open weights 75.8

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
DeepSeek: DeepSeek V4 Flash T
Reasoning Tools JSON Open weights 73.3

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
NVIDIA: Nemotron 3 Ultra 550B A55B T
Reasoning Tools Open weights 67.7

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
Poolside: Laguna XS 2.1 T
Reasoning Tools Open weights 63.1

Agentic coding model from Poolside in the XS size class for local deployment

poolside/laguna-xs-2.1 2026-07-02 262.144K context $0.06/M input $0.12/M output
6 providers
NVIDIA: Nemotron 3.5 Lightning 30B A3B T
Reasoning Tools JSON Open weights 39.3

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