VerdictPal
Join

Models / Alibaba

Qwen3.5 27B (Reasoning)

Qwen3.5 27B · Released 2026-02-24

AA Intelligence Index 33.8. Listed on Artificial Analysis with API pricing $0.3/$2.4 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.

#77 of 131 on AA Index · current snapshot
34 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite56
ContextUnlisted
Input / 1M$0.30
Output / 1M$2.4
Knowledge cutoffunpublished
Output speed0 t/s
TTFT (default API)0.00s
Statussolid
ReasoningCodingAgenticLong context
Reasoning
86
Coding
40
Agentic
94
Long context
67

72average across 4 tested families

Benchmark placements

Where Qwen3.5 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
τ³-Bench BankingAgentic#12/ 14394Artificial Analysis2026-07-28
IFBenchReasoning#27/ 12176Artificial Analysis2026-07-28
AA-LCRLong context#49/ 14367Artificial Analysis2026-07-28
GPQA DiamondReasoning#71/ 14986Artificial Analysis2026-07-28
Humanity's Last ExamReasoning#85/ 14422Artificial Analysis2026-07-28
Artificial Analysis Intelligence IndexReasoning#90/ 14734Artificial Analysis2026-07-28
SciCodeCoding#107/ 14440Artificial Analysis2026-07-28
Terminal-BenchAgentic#119/ 14833Artificial Analysis2026-07-28
AA output speedPerformance#148/ 149Artificial Analysis2026-07-28
AA time to first tokenPerformance#148/ 149Artificial Analysis2026-07-28
Family context

The three highest-scoring carded models in each capability family. Where Qwen3.5 27B (Reasoning) shows up, it's highlighted.

ReasoningQwen3.5 27B (Reasoning) · 86
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
CodingQwen3.5 27B (Reasoning) · 40
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticQwen3.5 27B (Reasoning) · 94
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextQwen3.5 27B (Reasoning) · 67
  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 Qwen3.5 27B (Reasoning) in the last 120 days. Older rows live in the full table below.

10 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context67.33%Artificial Analysis4
AA output speedPerformance0 t/sArtificial Analysis4
AA time to first tokenPerformance0.00sArtificial Analysis4
Artificial Analysis Intelligence IndexReasoning33.8%Artificial Analysis4
GPQA DiamondReasoning85.8%Artificial Analysis4
Humanity's Last ExamReasoning22.2%Artificial Analysis4
IFBenchReasoning75.58%Artificial Analysis4
SciCodeCoding39.5%Artificial Analysis4
τ³-Bench BankingAgentic93.86%Artificial Analysis4
Terminal-BenchAgentic32.58%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.

Reasoning86
Coding40
Agentic94
Long context67
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 Qwen3.5 27B (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 Qwen3.5 27B (Reasoning).

Reasoning

Coding

Agentic

Long context

Performance

Sources