China Mobileproprietary
Released: 2026-11-11Artificial Analysis

JT-4.1 Flash 236B A21B

JT-4.1 Flash 236B A21B from China Mobile, tracked on the Artificial Analysis Intelligence Index.

Intelligence Index
19.0/ 100
Artificial Analysis Intelligence Index (independent composite)
Throughput Speed
—tok/sec
Output streaming throughput
Time to First Answer
—ms
Time to first answer token, including any thinking
Cost to Run the Index
—USD
Artificial Analysis cost of the full Index run

Measured results · Artificial Analysis

Independent evaluations of JT-4.1 Flash 236B A21B. Values are reported as published; nothing here is estimated or derived. Snapshot 2026-11-15.

Intelligence Index
18.9
Cost to run the Index
—
Time per task
—
Omniscience index
2.0
Reasoning model
Yes
Cached-input price
—

Reasoning & knowledge

Agentic work

Long context & documents

Full analysis on Artificial Analysis

Headline Evaluation Breakdown

Six independently measured evaluations (Artificial Analysis)
Reasoning · CritPt v2 (Hard)19.0%
Coding & agents · Terminal-Bench 4.015.7%

Sourced Benchmark Evaluations (9)

Verified performance across authoritative benchmarks with provenance tracking.
BenchmarkStatusScoreTrustDateSource TypeProvenance
Terminal-Bench 4.0Active15.7%
93
2026-11-15independentSource ↗
Terminal-Bench-Science 0.1Active0%
93
2026-11-15independentSource ↗
CritPt v2 (Hard)Active19%
93
2026-11-15independentSource ↗
HLE-DiamondActive16.4%
93
2026-11-15independentSource ↗
AA-Omniscience (Accuracy)Active37.9%
93
2026-11-15independentSource ↗
AA-Omniscience (Non-Hallucination)Active42.1%
93
2026-11-15independentSource ↗
FrontierCode-AA 2.0Active7%
93
2026-11-15independentSource ↗
GDP.pdfActive6.6%
93
2026-11-15independentSource ↗
AutomationBench-AAActive36.7%
93
2026-11-15independentSource ↗
OpenAI Compatible API ExecutionAPI Ready
from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="china-mobile-jt-4-1-flash-236b-a21b",
    messages=[{"role": "user", "content": "Evaluate multi-step logic problem"}],
    temperature=0.2
)
print(response.choices[0].message.content)

Evaluation & Sourcing Notes

Scores listed for JT-4.1 Flash 236B A21B represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.

All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.