JT-4.1 Flash 236B A21B
JT-4.1 Flash 236B A21B is capable in long context, reasoning, and factuality; and behind the leaders in agentic tasks, coding, and multimodal tasks. Too few results yet to rate safety, math, multilingual tasks, or instruction following.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Safety, Math, Multilingual or Instruction Following.
Price
No current price is tracked for this model. See the rate card
Evidence
24results on16benchmarks
- 24 aggregator
From 1 source · latest Oct 8, 2026 · How verification works
JT-4.1 Flash 236B A21B benchmark results
24 results on 16 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
14.0% behind the leader1 of 3 ranked benchmarks measured
- 78.33Oct 8, 2026
Show 1 more long context resultHide 1 long context result
- 71.33Oct 8, 2026
19.6% behind the leader3 of 6 ranked benchmarks measured
- GPQA Diamond84.55Oct 8, 2026gpqa
- Humanity's Last Exam43.56Oct 8, 2026aa_hle
- 14.00Oct 8, 2026
Show 2 more reasoning resultsHide 2 reasoning results
- 0.00Oct 8, 2026
- Humanity's Last Exam17.79Oct 8, 2026aa_hle
20.2% behind the leader2 of 4 ranked benchmarks measured
- AA-Omniscience · Accuracy49.40Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination43.02Oct 8, 2026omniscienceNonHallucination
Show 2 more factuality resultsHide 2 factuality results
- AA-Omniscience · Accuracy24.28Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination56.33Oct 8, 2026omniscienceNonHallucination
27.4% behind the leader3 of 7 ranked benchmarks measured
- τ-Bench V3 · Banking28.04Aug 10, 2026tauBanking
- 41.40Oct 8, 2026
- Terminal-Bench 4.03.03Oct 8, 2026
Show 1 more agentic resultHide 1 agentic result
- 31.20Oct 8, 2026
33.4% behind the leader2 of 10 ranked benchmarks measured
- SciCode51.97Oct 8, 2026aa_scicode
- Terminal-Bench 2.159.55Oct 8, 2026terminalbenchV21
34.8% behind the leader1 of 6 ranked benchmarks measured
- MMMU-Pro64.10Oct 8, 2026aa_mmmu_pro
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- AA Intelligence27.29Oct 8, 2026aa_intelligence_index
- -8.78Oct 8, 2026
- AA Intelligence33.92Oct 8, 2026aa_intelligence_index
- 20.57Oct 8, 2026
- Artificial Analysis Coding Index52.43Sep 9, 2026aa_coding_index
- 34.91Aug 10, 2026
JT-4.1 Flash 236B A21B: common questions
Who makes JT-4.1 Flash 236B A21B?
JT-4.1 Flash 236B A21B is made by China Mobile.
When was JT-4.1 Flash 236B A21B released?
JT-4.1 Flash 236B A21B was released on Jul 9, 2026, according to Artificial Analysis.
What is JT-4.1 Flash 236B A21B good at?
JT-4.1 Flash 236B A21B is capable in long context, reasoning, and factuality; and behind the leaders in agentic tasks, coding, and multimodal tasks. Too few results yet to rate safety, math, multilingual tasks, or instruction following.
How many benchmarks has JT-4.1 Flash 236B A21B been tested on?
We track 24 results for JT-4.1 Flash 236B A21B on 16 benchmarks from 1 source. The latest was recorded on Oct 8, 2026.
About this record
Where JT-4.1 Flash 236B A21B's numbers come from, and every name it appears under.
- Tracked since
- Jul 10, 2026
- Newest source mention
- Oct 4, 2026
Where the results come from
Verification: 24 scores · 0 independently verified · 24 aggregator-attributed. How these tiers are assigned
From 1 source on 1 site. Artificial Analysis supplies all of them. Bars are coloured by trust tier.
- artificialanalysis.ai24