Alibaba Cloud / Qwen Team · apache_2_0

Qwen3.6-27B

Qwen3.6-27B by Alibaba Cloud / Qwen Team appears in 1 source with Reasoning at 45.74. Best read for Code quality, Low cost, Multimodal.

CreatorAlibaba Cloud / Qwen Team

Release date2026-04-21

Knowledge cutoffNot published

Context262K tokens

Input price$0.6/M tokens

Output price$3.6/M tokens

Modalitytext + vision

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank41ranking · source_rank

Reasoning45.74reasoning · index_reasoning

Math42.79math · index_math

Coding34.33coding · index_code

Vision30.2multimodal · index_vision

Tool calling23.45tool_calling · index_tool_calling

Long context29.12long_context · index_long_context

Finance46.09domain · index_finance

Legal46.13domain · index_legal

Healthcare45.92domain · index_healthcare

GPQA87.8 %reasoning · gpqa_score

SWE-bench Verified77.2 %coding · swe_bench_verified_score

Code Arena1,061.72 %coding · coding_arena_score

Humanity Last Exam24 %reasoning · hle_score

MMMU82.9 %multimodal · mmmu_score

MMMU-Pro75.8 %multimodal · mmmu_pro_score

SWE-bench Pro53.5 %coding · swe_bench_pro_score

CharXiv-R78.4 %multimodal · charxiv_r_score

Context262,144 tokenscontext · context

Speed187.15 c/sperformance · throughput

Latency13,599.36 msperformance · latency

Input price0.6 $/Mpricing · input_price

Output price3.6 $/Mpricing · output_price

Parameters27,781,427,952 paramsmodel · params

Evidence

Citations and source overlap

LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is Qwen3.6-27B verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.