Qwen3.5 397B A17B

Qwen3.5 397B A17B is a model from Alibaba. 6 benchmarks count toward its score, in 4 categories.

partialShows if the model has enough results for an index.
IndexOverall score out of 100.Unranked
CoverageShare of the index weight with results.60%
SpeedOutput tokens per second.12/s
Input / 1MUS dollars per 1M input tokens.$0.55
Output / 1MUS dollars per 1M output tokens.$3.5
ContextMaximum tokens in one request.262K
EloLMArena rating and rank.1438 (#71)

The index is a score out of 100. The ± range shows how much it can change.

77,007 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
58.3
CodingCode writing and repair.
N/A
ReasoningLogic problems and puzzles.
46.7
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
58.0
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
N/A
MathMath problems.
53.3

Results

6 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
τ²-bench TelecomAgentic97.8%69.0enabled effort · Sierra2 Mar 2026Sierra Research
GPQA diamondKnowledge86.4%58.0none effortEpoch AI
τ²-bench RetailAgentic84.4%59.4enabled effort · Sierra30 Apr 2026Sierra Research
OTIS Mock AIME 2024-2025Math82.2%57.5none effortEpoch AI
τ²-bench AirlineAgentic81.5%57.3enabled effort · Sierra2 Mar 2026Sierra Research
FrontierMath-Tiers-1-3-v2-PrivateMath31.2%49.0none effortEpoch AI
Mystery Game PuzzlesReasoning18.0%53.1none effortEpoch AI
Chess PuzzlesReasoning13.0%40.3none effortEpoch AI
τ²-bench BankingAgentic9.8%5.9enabled effort · Sierra4 Aug 2026Sierra Research

6 benchmarks count, from 9 of 9 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 statedSierra Research, collected directlyMIT — results are in the licensed repositoryEpoch AI, collected directlyCC BY — free to use and redistribute with attribution

More from Alibaba

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