ModelBench
Model catalog

Models

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

Compare Export CSV
10 models
requesty Open weights
Ranked by GPQA Diamond
Alibaba Qwen: Qwen3.8 Flash Next T
Reasoning Tools JSON Open weights 91.7

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
Zhipu AI: GLM-5.2 T
Reasoning Tools JSON Open weights 91.2

Open flagship GLM for long-horizon coding agents and million-token context work

zhipuai/glm-5.2 2026-06-13 1M context $1.195/M input $4.183/M output
81 providers
DeepSeek: DeepSeek V4.1 Flash T
Reasoning Tools JSON Open weights 90.9

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
Tencent: Hy3 T
Reasoning Tools Open weights 90.4

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 Pro T
Reasoning Tools JSON Open weights 90.1

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
Meta: Muse Spark Open T
Reasoning Tools JSON Open weights 89.0

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 Flash T
Reasoning Tools JSON Open weights 88.1

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
Xiaomi: MiMo-V2.5-Pro T
Reasoning Tools JSON Open weights 86.6

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

xiaomi/mimo-v2.5-pro 2026-04-22 1.04858M context $0.435/M input $0.87/M output
26 providers
Meta: Muse Glimmer 30B T
Reasoning Tools Open weights 83.5

Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.

meta/muse-glimmer-30b 2026-08-10 131.072K context $0.2/M input $0.8/M output
12 providers
NVIDIA: Nemotron 3.5 Lightning 30B A3B T
Reasoning Tools Open weights 75.4

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