Nanbeige

Nanbeige4.3-33B

ReasoningOpen weightsHugging Face
Intelligence
20.4
Rank 252 of 768 measured models
Output speed
159 t/s
Rank 87 of 425 measured models
Context window
524K
Rank 589 of 1296 measured models

Nanbeige4.3-33B scores 20.4 on the Artificial Analysis Intelligence Index, ranking 252nd of 768 measured models. The closest models on this index are GPT-5.1 Codex mini (High) (20.4), Qwen3.5 Omni Plus (20.4), and o3 (20.2). With an output speed of 159 t/s, it is faster than Qwen3.5 Omni Plus (117 t/s) and o3 (151 t/s), slower than GPT-5.1 Codex mini (High) (175 t/s).

Artificial Analysis Indices
Intelligence20.4
Rank 252 of 768 measured models
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Finance & Accounting32.7
Rank 118 of 241 measured models
Strategy & Ops36.0
Rank 118 of 241 measured models
Legal27.2
Rank 144 of 241 measured models
Engineering26.8
Rank 139 of 240 measured models
Economics29.4
Rank 165 of 248 measured models
Standard Benchmarks
Terminal-Bench 4.029.8%
Rank 55 of 240 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy