Advertise here
#124

Qwen3.5-122B-A10B

Qwen Release: 2026-02-24 Tested on: 2026-05-21 23:57 qwen/qwen3.5-122b-a10b::none
122B total (10B active)MoEOpen source
(medium) (none)

Summary

Qwen3.5-122B-A10B scores 5.4 on AI BENCHY and ranks #124. It has 10.0 reliability, a 35.0% pass rate, $0.023 total cost, and 3.38s average response time.

What makes Qwen3.5-122B-A10B unique: It stands out most in Domain specific, where it ranks #3, while Anti-AI Tricks is its weakest area at #18. Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.

Model facts

Researched on 2026-08-12

Reported
Parameters
122B total (10B active)
Architecture
MoE
Availability
Open source
License
Apache-2.0
Parameter source Availability source

Score

5.4

Consistency

9.2

Reliability

10.0

Total Cost (Current Price)

$0.023

Total Output Tokens

3,375

Total Input Tokens

0

Input Price

$0.260 / 1M

Output Price

$2.080 / 1M

Cache Read Price

N/A

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 14

Attempt pass rate: 35.0%

Flaky tests

2

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

3.38s

Response Time (max): 46.00s

Response Time (total): 67.64s

Wrong answer: 12 Did not follow instructions: 2

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#124 Qwen3.5-122B-A10B

none
Cost
$0.016
Time
44.5s
Tokens
6,431 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 01:51 Re-test 5.7 10.0 $0.283 ↑ Compare
2026-07-16 22:04 New test added 5.7 10.0 $0.247 ↓ Compare
2026-06-04 13:26 New test added 5.3 10.0 $0.020 ↓ Compare
2026-05-21 23:57 Suite changed 5.4 10.0 $0.023 Current run
2026-04-11 01:44 First recorded run 5.7 N/A $0.022 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-05-21 23:57 · Suite changed60/60 attempts5.49.210.06/2023,3750$0.0233.38s
2026-07-16 22:04 · New test added66/66 attempts5.79.310.06/22288,458241,566$0.24712.92s
Difference—-0.3-0.10.000-85083-241566-$0.225-9537ms

Benchmark coverage differs: 60/60 attempts (Target: 3 repeats per test) versus 66/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Qwen3.5-122B-A10BnonevsLaguna XS 2.1mediumFree AvailableQwen3.5-122B-A10BnonevsGemini 3 Flash PreviewnoneQwen3.5-122B-A10BnonevsGrok 4.3mediumQwen3.5-122B-A10BnonevsSolar Pro 4mediumQwen3.5-122B-A10BnonevsKAT-Coder-Pro V2.5highQwen3.5-122B-A10BnonevsKimi K2.5mediumQwen3.5-122B-A10BnonevsGLM 5.1noneQwen3.5-122B-A10BnonevsMercury 2.5mediumQwen3.5-122B-A10BnonevsGLM 5.3lowQwen3.5-122B-A10BnonevsGemini 3.5 Flashminimal

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 4.8 10.0
Coding 4.0 5.5
Combined 3.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 5.0 10.0
Instructions following 6.3 10.0
Puzzle Solving 3.7 7.7
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models