Alibaba Cloud / Qwen Team · apache_2_0

Qwen3.5-122B-A10B

Qwen3.5-122B-A10B by Alibaba Cloud / Qwen Team appears in 2 sources with Reasoning at 43.05. Best read for Code quality, Coding, High intelligence.

CreatorAlibaba Cloud / Qwen Team

Release date2026-02-24

Knowledge cutoffNot published

Context262K tokens

Input price$0.4/M tokens

Output price$3.2/M tokens

Modalitytext + vision

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank73ranking · source_rank

Reasoning43.05reasoning · index_reasoning

Math44.02math · index_math

Coding25.78coding · index_code

Research22.12research · index_search

Writing24.23writing · index_communication

Vision30.67multimodal · index_vision

Tool calling13.44tool_calling · index_tool_calling

Long context32.33long_context · index_long_context

Finance48.68domain · index_finance

Legal48.75domain · index_legal

Healthcare47.37domain · index_healthcare

GPQA86.6 %reasoning · gpqa_score

SWE-bench Verified72 %coding · swe_bench_verified_score

Code Arena748.78 %coding · coding_arena_score

Humanity Last Exam47.5 %reasoning · hle_score

MMMLU86.7 %reasoning · mmmlu_score

MMMU83.9 %multimodal · mmmu_score

MMMU-Pro76.9 %multimodal · mmmu_pro_score

BrowseComp63.8 %research · browsecomp_score

CharXiv-R77.2 %multimodal · charxiv_r_score

ScreenSpot Pro70.4 %multimodal · screenspot_pro_score

Context262,144 tokenscontext · context

Speed132.78 c/sperformance · throughput

Latency30,143.7 msperformance · latency

Input price0.4 $/Mpricing · input_price

Output price3.2 $/Mpricing · output_price

Parameters122,000,000,000 paramsmodel · params

Arena Rating1,419.51metric

Arena Rank69metric

Vote Count21,417metric

Evidence

Citations and source overlap

Arena AILM Arena text leaderboard (overall) mirrored in the public leaderboard dataset.Retrieved 2026-05-20 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 Qwen3.5-122B-A10B 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.