Qwen3.5-122B-A10B

Qwen3.5-122B-A10B is a reasoning model from Alibaba. 24 benchmarks count toward its score, in 6 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.52.3 ±4.8
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.76/s
Input / 1MUS dollars per 1M input tokens.$0.26
Output / 1MUS dollars per 1M output tokens.$2.08
ContextMaximum tokens in one request.262K
EloLMArena rating and rank.1418 (#113)

50 is the middle of the board. The range shows the doubt in the index.

28,359 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category. 50 is the middle.

50 is the middle
AgenticMulti-step tasks with tools.
51.9
CodingCode writing and repair.
51.5
ReasoningLogic problems and puzzles.
50.9
MultimodalTasks with images and text.
54.7
KnowledgeFacts and expert knowledge.
51.8
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
59.2
MathMath problems.
N/A

Results

24 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result on the index scale.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
τ²-Bench Tool-Agent-User EvaluationAgentic93.6%66.0Victor Barres et al.
Instruction-Following EvalInstruction93.4%52.5Jeffrey Zhou et al.
V*Multimodal93.2%53.1Z.AI
Massive Multitask Language Understanding ProfessionalKnowledge86.7%57.1Yubo Wang et al.
Graduate-Level Google-Proof Q&AKnowledge86.6%58.2David Rein et al.
MathVisionMultimodal86.2%Qwen
Artificial Analysis GPQA DiamondKnowledge85.7%56.4Artificial Analysis
Massive Multi-discipline Multimodal UnderstandingMultimodal83.9%53.1MMMU authors
MMLU-ProXMultilingual82.2%MMLU-ProX authors
CharXiv ReasoningMultimodal77.2%54.0CharXiv authors
Artificial Analysis Long Context ReasoningReasoning76.3%61.0Artificial Analysis
Artificial Analysis IFBenchInstruction75.7%65.9Artificial Analysis
Artificial Analysis MMMU-ProMultimodal75.0%58.7Artificial Analysis
Multimodal Multi-disciplinary Video UnderstandingMultimodal74.7%MMVU benchmark maintainers
Software Engineering Benchmark VerifiedCoding72.0%55.3Carlos E. Jimenez et al.
SuperGPQA: Scaling LLM Evaluation Across 285 Graduate DisciplinesKnowledge67.1%53.0Xiaoxuan Du et al.
BrowseCompAgentic63.8%53.5OpenAI
LongBench v2Reasoning60.2%LongBench v2 authors
OSWorld-VerifiedAgentic58.0%47.7Tianbao Xie et al.
Artificial Analysis Coding IndexCoding45.7%51.2Artificial Analysis
Artificial Analysis SciCodeCoding39.7%48.0Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge25.2%51.9Artificial Analysis
Artificial Analysis Omniscience AccuracyKnowledge24.4%44.1Artificial Analysis
Mystery Game PuzzlesReasoning17.0%52.0none effortEpoch AI
Artificial Analysis Intelligence IndexKnowledge15.6%41.9Artificial Analysis
GDPval-AA normalizedAgentic15.1%47.2Artificial Analysis
Artificial Analysis Agentic IndexAgentic9.6%45.0Artificial Analysis
Critical Physics TasksReasoning0.6%39.6Artificial Analysis

24 benchmarks count, from 24 of 28 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsOpenRouter, collected directlyNo licence statedEpoch AI, collected directlyCC BY — free to use and redistribute with attribution

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeApodex 1.1 Mini59.1 · Free

More from Alibaba

Qwen3.8 Max68.4Qwen3.8-Flash-Next66.4Qwen3.8 Max Preview69.0Qwen3.8-27B63.1Qwen3.7 Max62.6