Inference
EN
Alibaba

Qwen3.5 397B (Reasoning)

Qwen3.5 397B (Reasoning) is a reasoning model from Alibaba in the Qwen3.5 397B family. 9 benchmarks count toward its index, in 6 categories.

  • Open weights
  • Reasoning
  • Input: text
  • Released 2026-02
RankedEnough results for an index.
IndexAll categories, out of 100.55.3±6.9Median 51.0
CoverageIndex weight that has results.85%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.60Median $0.60
Output / 1MUS dollars per 1M output tokens.$3.60Median $2.55
ContextMaximum tokens in one request.128KMedian 262K
EloLMArena rating and rank.—Median 1422

Run locally

403.4B parameters
16-bit
848.1 GB
8-bit
451.0 GB
4-bit
257.8 GB
Weights
Hugging Face (opens in a new tab) ↗

Memory need with a short context. The 4-bit copy needs more than 128 GB. Compare local models

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.2 counted59.474 / 218
CodingCode writing and repair.1 counted54.2—
ReasoningLogic problems and puzzles.2 counted50.2114 / 227
MultimodalTasks with images and text.1 counted55.8—
KnowledgeFacts and expert knowledge.2 counted56.384 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted62.7—
MathMath problems.None counted——

Results

9 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Artificial Analysis IFBenchInstruction78.8%6 / 146
τ²-Bench Tool-Agent-User EvaluationAgentic95.6%18 / 149
Artificial Analysis GPQA DiamondKnowledge89.3%45 / 199
Artificial Analysis MMMU-ProMultimodal77.3%40 / 113
Artificial Analysis Long Context ReasoningReasoning77.3%77 / 217
Artificial Analysis Humanity's Last ExamKnowledge29.0%85 / 222
Critical Physics TasksReasoning1.7%109 / 214
Artificial Analysis SciCodeCoding44.8%74 / 114
APEX-Agents-AAAgentic15.3%21 / 30

Sources

BenchLMCC BY-NC 4.0

History

5 releases
Index45.6 → 55.3
23 Oct 202612 Nov 2026
Output / 1M$3.60 → $3.60
23 Oct 202612 Nov 2026

Questions

How much does Qwen3.5 397B (Reasoning) cost?
$0.60 per 1M input tokens, $3.60 per 1M output tokens.
How good is Qwen3.5 397B (Reasoning)?
Its index is 55.3 out of 100. That is place 99 of 283 ranked models.
What is Qwen3.5 397B (Reasoning) best at?
Knowledge: 56.3 out of 100, place 84 of 268.
What is the context window of Qwen3.5 397B (Reasoning)?
128K tokens.
Is Qwen3.5 397B (Reasoning) open source?
Yes. Its weights are published.
When was Qwen3.5 397B (Reasoning) released?
February 2026.

Badge

Qwen3.5 397B (Reasoning) on Inference360: place 99 of 283, index 55.3
HTML
<a href="https://inference360.ai/models/qwen3-5-397b-reasoning"><img src="https://inference360.ai/badges/qwen3-5-397b-reasoning.svg" alt="Qwen3.5 397B (Reasoning) on Inference360: place 99 of 283, index 55.3" height="20"></a>
Markdown
[![Qwen3.5 397B (Reasoning) on Inference360: place 99 of 283, index 55.3](https://inference360.ai/badges/qwen3-5-397b-reasoning.svg)](https://inference360.ai/models/qwen3-5-397b-reasoning)

Compare with

GPT-5.155.3Step 3.7 Flash55.3Apodex 1.1 Mini55.7Qwen3.5 397B53.8Qwen3 Max45.0

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeGLM-5.3-Flash63.1 · $0.078/1M

More from Alibaba

All models
Qwen3.5 397B53.8Qwen3.5 397B A17BUnrankedQwen3.5 Plus 2026-02-15UnrankedQwen3 Max ThinkingUnrankedQwen3 Coder NextUnranked