VerdictPal
Join

Models / Alibaba

Qwen3.6 27B (Reasoning)

Qwen3.6 27B · Released 2026-04-22

AA Intelligence Index 37.1. Listed on Artificial Analysis with API pricing $0.6/$3.6 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.

#120 of 184 on AA Index · current snapshot
22 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite49
Context128K
Input / 1M$0.60
Output / 1M$3.6
Knowledge cutoffopen
Output speed58 t/s
TTFT (default API)1.36s
Statussolid

Family profile

Best published score in each covered benchmark family.

66/100 avg
Reasoning
84
Coding
43
Agentic
61
Long context
77

4 tested benchmark families

Benchmark placements

Where Qwen3.6 27B (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 time to first tokenPerformance#50/ 190Artificial Analysis2026-09-10
IFBenchReasoning#62/ 12768Artificial Analysis2026-09-10
AA output speedPerformance#66/ 190Artificial Analysis2026-09-10
AA-LCRLong context#68/ 18277Artificial Analysis2026-09-10
SciCodeCoding#70/ 9443Artificial Analysis2026-09-10
τ³-Bench BankingAgentic#72/ 11117Artificial Analysis2026-09-10
Terminal-BenchAgentic#74/ 18961Artificial Analysis2026-09-10
GPQA DiamondReasoning#112/ 19084Artificial Analysis2026-09-10
Humanity's Last ExamReasoning#114/ 18523Artificial Analysis2026-09-10
Artificial Analysis Intelligence IndexReasoning#125/ 18822Artificial Analysis2026-09-10
Family context

The three highest-scoring models with pages in each capability family. Where Qwen3.6 27B (Reasoning) shows up, it's highlighted.

ReasoningQwen3.6 27B (Reasoning) · 84
  1. 1
    GPT-6 Astra
    96
  2. 2
    Claude Mythos Preview
    95
  3. 3
    Gemini 3.7 Flash
    95
CodingQwen3.6 27B (Reasoning) · 43
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticQwen3.6 27B (Reasoning) · 61
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextQwen3.6 27B (Reasoning) · 77
  1. 1
    Kimi K3
    89
  2. 2
    Claude Fable 5.1
    85
  3. 3
    GPT-5.5 (high)
    84
Newest receipts

Benchmark rows added to the public ledger for Qwen3.6 27B (Reasoning) in the last 120 days. Older rows live in the full table below.

10 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context77.33%Artificial Analysis4
AA output speedPerformance58 t/sArtificial Analysis4
AA time to first tokenPerformance1.36sArtificial Analysis4
Artificial Analysis Intelligence IndexReasoning21.9%Artificial Analysis4
GPQA DiamondReasoning84.2%Artificial Analysis4
Humanity's Last ExamReasoning23.1%Artificial Analysis4
IFBenchReasoning67.55%Artificial Analysis4
SciCodeCoding42.8%Artificial Analysis4
τ³-Bench BankingAgentic16.7%Artificial Analysis4
Terminal-BenchAgentic60.67%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
Coding43
Agentic61
Long context77
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.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaxAIMiniMaxZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Qwen3.6 27B (Reasoning). Scores link to the original source; gaps mean no public row exists yet.

10 sourced rows

10 of 37 catalog benchmarks have a sourced row for Qwen3.6 27B (Reasoning).

Reasoning

Coding

Agentic

Long context

Performance

Sources