Nex AGI's open-source agentic reasoning model, post-trained on Qwen3.5-397B-A17B. It is built for agentic coding, software engineering, deep research, tool use, and long-horizon tasks with a 256K context window.
Added Jun 4, 2026
Model weightsContext Window
262.1K
Max Output
262.1K
Input Price (Auto)
$0.50/1M
Output Price (Auto)
$2.50/1M
Cache Read (Auto)
$0.25/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Coding Index
59.1
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
89.2%
Better than 89% of models compared
HLE
Humanity's Last Exam
33.7%
Better than 89% of models compared
IFBench
Instruction-following benchmark
66.2%
Better than 78% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
81.6%
Better than 72% of models compared
AA-LCR
Long context reasoning evaluation
76.3%
Better than 92% of models compared
GDPval-AA
Economically valuable tasks
37.5%
CritPt
Research-level physics reasoning
8.6%
Coding
SciCode
Python programming for scientific computing
41.8%
Better than 76% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
34.8%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
94.9%
Last updated Aug 11, 2026, 12:00 PM
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Nex N2 Pro with similar models from the same provider or model family.
Nex N2 Mini
nex-agi/nex-n2-miniNex AGI's open-source agentic mixture-of-experts model in the Nex N2 family. It accepts text and image input and is built for coding, tool use, structured outputs, and optional reasoning with a 256K context window.
DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-0813DeepSeek V4 Pro 0813 is the general-availability release of DeepSeek V4 Pro, built for coding, tool use, cybersecurity, automation, and long-horizon agent workflows. DeepSeek reports strong gains over the preview and scores above Opus 4.8 on Terminal Bench 2.1, Cybergym, DeepSWE, and AutomationBench. It supports a 1M-token context window.
DeepSeek V4 Pro 0813 Thinking
deepseek/deepseek-v4-pro-0813:thinkingDeepSeek V4 Pro 0813 Thinking enables reasoning by default on the general-availability release of DeepSeek V4 Pro, built for coding, tool use, cybersecurity, automation, and long-horizon agent workflows. DeepSeek reports strong gains over the preview and scores above Opus 4.8 on Terminal Bench 2.1, Cybergym, DeepSWE, and AutomationBench. It supports a 1M-token context window.
Solar Pro 4
upstage/solar-pro4Upstage's Solar Pro 4 is a long-context language model for agentic workflows, office productivity, document-intensive work, and coding. This variant keeps reasoning disabled for faster direct responses.
Solar Pro 4 Thinking
upstage/solar-pro4:thinkingUpstage's Solar Pro 4 with reasoning enabled for harder agentic workflows, document-intensive work, coding, planning, and analysis across a 524K-token context window.
MiMo V2.5 Pro (Crof)
xiaomi/mimo-v2.5-pro-crofMiMo V2.5 Pro is Xiaomi's long-context flagship general model for coding and agentic orchestration. This separately served variant is intended for users concerned about censorship on the regular Xiaomi MiMo V2.5 Pro, and it is included in the NanoGPT subscription.