ModelBench
Model catalog

Models

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

Compare Export CSV
5 models
nano-gpt 1M+
Ranked by LiveCodeBench
DeepSeek: DeepSeek V4 Pro T
Reasoning Tools JSON Open weights 93.5

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
Sakana: Fugu Ultra T
Reasoning Tools JSON 93.2

Quality-first multi-agent model for hard research, analysis, and competitions

sakana/fugu-ultra 2026-06-15 1M context $5/M input $30/M output
14 providers
DeepSeek: DeepSeek V4 Flash T
Reasoning Tools JSON Open weights 91.6

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 Open weights 89.0

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
Reflection: Beam 1.0 501B A23B T
Reasoning Tools JSON Open weights 88.3

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