Why does Nanbeige4.3-33B have no BenchLeader Index score?

The index needs at least five independent results across at least two categories, and as of 2 Nov 2026 Nanbeige4.3-33B does not have them yet. Launch-post scores are never used, so it is ranked once independent publishers have measured it.

When was Nanbeige4.3-33B released?

Nanbeige released Nanbeige4.3-33B on 25 Oct 2026.

NanbeigeOpen weightsReasoning modelNewFirst seen 2 Nov 2026 on one source; awaiting a secondCompare with another model

Nanbeige4.3-33B

Speed#46 of 211

159tokens/s

Top quarter

1.9× the median

As of 2 Nov 2026, Nanbeige4.3-33B by Nanbeige is not yet ranked on the BenchLeader Index, which needs at least five independent results across two categories. It streams about 160 tokens/s (Artificial Analysis). Released 25 Oct 2026.

Key facts (as of 2 Nov 2026)

Nanbeige4.3-33B streams about 160 tokens/s (Artificial Analysis, 2 Nov 2026).
Nanbeige4.3-33B was released on 25 Oct 2026 (Nanbeige).

In detail. Nanbeige4.3-33B is a Nanbeige open-weights reasoning model, released 25 Oct 2026. It is not yet ranked: the index needs at least five independent results across two categories. Output speed of 159 tokens per second puts it in the fastest quarter, with a first answer in 14.0 s. Last measured 25 Oct 2026.

Blended price: –
Output speed: 159 tok/s; measured by Artificial Analysis
First answer: 14 s
Context: 524k; via Artificial Analysis
Full answer: 17 s; median, reasoning included
Cost per task: –
Tokens per task: 158k; 64% of it reasoning
Released: 25 Oct 2026

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Reasoning37
Coding39
Knowledge43

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	not stated	Source
HLE-Diamond (AA)	6.9%#109	Artificial Analysis
CritPt v2 hard subset (AA)	15.5%#77	Artificial Analysis

Coding

Benchmark	not stated	Source
Terminal-Bench 4.0 (AA)not in index	29.8%#53	Artificial Analysis
FrontierCode 2.0 (AA)	10.7%#72	Artificial Analysis

Agents & tools

Benchmark	not stated	Source
AutomationBenchnot in index	53.1%#79	Artificial Analysis
GDP.pdf (AA)not in index	11.2%#132	Artificial Analysis
AA-Briefcase v1.1not in index	1162#87	Artificial Analysis
Terminal-Bench-Science 0.1 (AA)not in index	0.9%#85	Artificial Analysis

Knowledge

Benchmark	not stated	Source
AA-Omniscience v1.1	-4.4#69	Artificial Analysis
AA-Omniscience v1.1: accuracynot in index	11.7%#105	Artificial Analysis
AA-Omniscience v1.1: non-hallucinationnot in index	81.8%#7	Artificial Analysis

Composite

Benchmark	not stated	Source
AA Intelligence Index v5.0not in index	20.4#68	Artificial Analysis
AA Progress Index v1not in index	306#107	Artificial Analysis

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

Workload	Tokens in / out	Cost	With caching	Time
Chat reply	400 / 300	–	–	15.9 s
Summarize a 30-page report	12,000 / 600	–	–	17.8 s
Code edit	6,000 / 1,500	–	–	23.4 s
Agentic coding session	60,000 / 4,000	–	–	39.1 s
Structured extraction	2,000 / 200	–	–	15.2 s

New this month

Questions people ask

Why does Nanbeige4.3-33B have no BenchLeader Index score?: The index needs at least five independent results across at least two categories, and as of 2 Nov 2026 Nanbeige4.3-33B does not have them yet. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
When was Nanbeige4.3-33B released?: Nanbeige released Nanbeige4.3-33B on 25 Oct 2026.

Data as of 2 Nov 2026. Compare with another model.

Cite as: BenchLeader, “Nanbeige4.3-33B: benchmarks, pricing, speed and rank”, data as of 2 Nov 2026, https://www.benchleader.com/models/nanbeige4-3-33b.