Back to LeaderboardCompare View
Model profile
Alibaba
New in 2026

Qwen3.5 122B A10B (Non-reasoning)

Qwen3.5 122B A10B (Non-reasoning) is a budget text-first model from Alibaba with a fast runtime profile, unknown context posture, and the clearest fit around agent workflows / reasoning.

Best for: Agent workflows / ReasoningFast latencyUnknown contextBudget pricing
Intelligence
35.9

Benchmark blend

Coding
31.6

Dev workflow signal

Context
N/A

Unknown

Input Price
$0.40

Budget tier

Decision snapshot
53

Qwen3.5 122B A10B (Non-reasoning) currently reads as a budget text-first option with unknown context and a fast runtime profile.

Overall profile
Use-case specific
Best for
Agent workflows / Reasoning
Latency tier
Fast
Price tier
Budget
Source coverage
OpenRouterArtificial Analysis
Compare this modelSee leaderboard

Decision Strip

Decision rail before the raw tables

Core buy-side signals stay in one pass. The rest of the page expands only after intelligence, speed, context, and price are clear.

Intelligence
35.9
36

General reasoning and benchmark headroom.

Limited
Speed
141 tok/s
90

TTFT 1.07s

Above average
Context
N/A
34

How much prompt and task state can stay in view.

Limited
Price
$0.40
86

$3.20 output / 1M

Efficient

Editorial Profile

Qwen3.5 122B A10B (Non-reasoning) in one narrative

Positioning, tradeoffs, and fit are consolidated into one read instead of repeating the same story across separate cards.

Use-case specificCoding score 32Math score 36

The Qwen3.5 122B A10B (Non-reasoning) AI model by Alibaba.

Identity

Alibaba text-first profile

Positioning

Agent workflows / Reasoning with unknown context and fast runtime.

Cost posture

Efficient spend profile. More comfortable for sustained prompt volume if the capability fit is right.

Strengths

  • Latency and throughput look responsive enough for interactive loops.

Tradeoffs

  • Budget-friendly input pricing is a strength, but raw capability may vary by workload.

  • Current metadata points to a text-first profile rather than a broad multimodal one.

Best fit

  • Focused chat, retrieval-augmented flows, and narrower production tasks.

Compare Next

Similar profiles worth opening next

Alibaba

Qwen3.5 397B A17B (Non-reasoning)

Intelligence
40.1
Context
N/A
Input Price
$0.60
CompareOpen profile
Alibaba

Qwen3.5 27B (Non-reasoning)

Intelligence
37.2
Context
N/A
Input Price
$0.30
CompareOpen profile
Alibaba

Qwen3.5 35B A3B (Reasoning)

Intelligence
37.1
Context
N/A
Input Price
$0.25
CompareOpen profile

Benchmarks

Grouped by job-to-be-done

Only benchmark categories with actual signal are shown. Secondary values stay as simple definitions instead of nested micro-cards.

General intelligence

Broad reasoning, knowledge depth, and flagship benchmark posture.

Intelligence Index
35.9
GPQA
82.7%
HLE
14.8%
Coding

Software implementation, debugging quality, and coding benchmark signal.

Coding Index
31.6
SciCode
35.6%
Agent / tool use

Long-horizon execution quality and interactive benchmark evidence.

IFBench
50.8%
TAU2
84.5%
TerminalBench Hard
29.5%
LCR
56.0%

Specs & Pricing

Technical snapshot and cost posture

Specs stay neutral, pricing gets emphasis through values rather than extra containers. Raw provider internals remain in metadata at the end.

Technical snapshot
Context Window
N/A
Vision
Text-first
Price architecture
Input
per 1M input tokens
$0.40
Output
per 1M output tokens
$3.20
Blended
AA 3:1 mix
$1.10

This model is relatively efficient on price. It is the easier fit when sustained prompt volume matters.

Metadata

Raw source tables at the end

Verification details remain available, but the page no longer forces them ahead of the editorial read.