VerdictPal
Join

Models / Other

JT-4.1 Flash 236B A21B

JT-4.1 Flash · Released 2026-07-09

AA Intelligence Index 38.8. Listed on Artificial Analysis with API pricing $0/$0 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

#64 of 168 on AA Index · current snapshot
40 AA Index · 8 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite51
Context128K
Input / 1MFree
Output / 1MFree
Knowledge cutoffopen
Statussolid

Family profile

Best published score in each covered benchmark family.

63/100 avg
Reasoning
85
Coding
38
Agentic
60
Long context
70

4 tested benchmark families

Benchmark placements

Where JT-4.1 Flash 236B A21B places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
Terminal-BenchAgentic#70/ 18460Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#75/ 18740Artificial Analysis2026-09-01
AA-LCRLong context#86/ 17970Artificial Analysis2026-09-01
GPQA DiamondReasoning#102/ 18585Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#130/ 18018Artificial Analysis2026-09-01
SciCodeCoding#143/ 18038Artificial Analysis2026-09-01
AA time to first tokenPerformance#154/ 186Artificial Analysis2026-09-01
AA output speedPerformance#155/ 187Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where JT-4.1 Flash 236B A21B shows up, it's highlighted.

ReasoningJT-4.1 Flash 236B A21B · 85
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
CodingJT-4.1 Flash 236B A21B · 38
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticJT-4.1 Flash 236B A21B · 60
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextJT-4.1 Flash 236B A21B · 70
  1. 1
    Muse Spark 1.2
    83
  2. 2
    Kimi K3
    83
  3. 3
    Gemini 3.5 Flash
    81
Newest receipts

Benchmark rows added to the public ledger for JT-4.1 Flash 236B A21B in the last 120 days. Older rows live in the full table below.

8 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context70.33%Artificial Analysis5
AA output speedPerformance0 t/sArtificial Analysis5
AA time to first tokenPerformance0.00sArtificial Analysis5
Artificial Analysis Intelligence IndexReasoning39.9%Artificial Analysis5
GPQA DiamondReasoning84.5%Artificial Analysis5
Humanity's Last ExamReasoning17.8%Artificial Analysis5
SciCodeCoding38.2%Artificial Analysis5
Terminal-BenchAgentic59.55%Artificial Analysis5
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning85
Coding38
Agentic60
Long context70
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for JT-4.1 Flash 236B A21B. Scores link to the original source; gaps mean no public row exists yet.

8 sourced rows

8 of 37 catalog benchmarks have a sourced row for JT-4.1 Flash 236B A21B.

Reasoning

Coding

Agentic

Long context

Performance

Sources