VerdictPal
Join

Models / Alibaba

Qwen3.6 35B A3B (Reasoning)

Qwen3.6 35B · Released 2026-04-16

AA Intelligence Index 31.6. Listed on Artificial Analysis with API pricing $0.248/$1.485 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.

#91 of 131 on AA Index · current snapshot
32 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite44
ContextUnlisted
Input / 1M$0.25
Output / 1M$1.5
Knowledge cutoffunpublished
Output speed108 t/s
TTFT (default API)1.41s
Statussolid
ReasoningCodingAgenticLong context
Reasoning
84
Coding
36
Agentic
45
Long context
64

57average across 4 tested families

Benchmark placements

Where Qwen3.6 35B A3B (Reasoning) 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
AA output speedPerformance#36/ 149Artificial Analysis2026-07-28
AA time to first tokenPerformance#40/ 149Artificial Analysis2026-07-28
IFBenchReasoning#71/ 12164Artificial Analysis2026-07-28
Terminal-BenchAgentic#79/ 14845Artificial Analysis2026-07-28
AA-LCRLong context#80/ 14364Artificial Analysis2026-07-28
GPQA DiamondReasoning#86/ 14984Artificial Analysis2026-07-28
Humanity's Last ExamReasoning#89/ 14420Artificial Analysis2026-07-28
Artificial Analysis Intelligence IndexReasoning#105/ 14732Artificial Analysis2026-07-28
SciCodeCoding#124/ 14436Artificial Analysis2026-07-28
τ³-Bench BankingAgentic#127/ 1439Artificial Analysis2026-07-28
Family context

The three highest-scoring carded models in each capability family. Where Qwen3.6 35B A3B (Reasoning) shows up, it's highlighted.

ReasoningQwen3.6 35B A3B (Reasoning) · 84
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
CodingQwen3.6 35B A3B (Reasoning) · 36
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticQwen3.6 35B A3B (Reasoning) · 45
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextQwen3.6 35B A3B (Reasoning) · 64
  1. 1
    GPT-5 (high)
    76
  2. 2
    GPT-5.2 Codex (xhigh)
    76
  3. 3
    Kimi K3
    75
Newest receipts

Benchmark rows added to the public ledger for Qwen3.6 35B A3B (Reasoning) in the last 120 days. Older rows live in the full table below.

10 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context63.67%Artificial Analysis4
AA output speedPerformance108 t/sArtificial Analysis4
AA time to first tokenPerformance1.41sArtificial Analysis4
Artificial Analysis Intelligence IndexReasoning31.6%Artificial Analysis4
GPQA DiamondReasoning84.1%Artificial Analysis4
Humanity's Last ExamReasoning20.2%Artificial Analysis4
IFBenchReasoning64.35%Artificial Analysis4
SciCodeCoding35.8%Artificial Analysis4
τ³-Bench BankingAgentic8.66%Artificial Analysis4
Terminal-BenchAgentic44.94%Artificial Analysis4
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.

Reasoning84
Coding36
Agentic45
Long context64
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotxAIMiniMaxMetaZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Qwen3.6 35B A3B (Reasoning). Scores link to the original source; gaps mean no public row exists yet.

10 sourced rows

10 of 32 catalog benchmarks have a sourced row for Qwen3.6 35B A3B (Reasoning).

Reasoning

Coding

Agentic

Long context

Performance

Sources