#68 Qwen3.5-122B-A10B
medium- Cost
- $0.019
- Time
- 48.7s
- Tokens
- 6,034 tok
Qwen
Release: 2026-02-24
Tested on: 2026-07-16 22:21
qwen/qwen3.5-122b-a10b::medium
122B total (10B active)MoEOpen source
(medium)
(none)
Summary
Qwen3.5-122B-A10B scores 7.1 on AI BENCHY and ranks #68. It has 10.0 reliability, a 71.2% pass rate, $1.046 total cost, and 64.16s average response time.
What makes Qwen3.5-122B-A10B unique: It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
Model facts
Researched on 2026-08-12
- Parameters
- 122B total (10B active)
- Architecture
- MoE
- Availability
- Open source
- License
- Apache-2.0
7.1
Consistency
8.5
10.0
Total Output Tokens
487,218
Total Input Tokens
124,771
Input Price
$0.260 / 1M
Output Price
$2.080 / 1M
Flaky tests
4
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 01:54 Re-test | 7.1 | 10.0 | $1.207 ↑ | Compare | |
| 2026-07-16 22:21 New test added | 7.1 | 10.0 | $1.046 ↓ | Current run | |
| 2026-06-04 13:31 New test added | 7.8 | 10.0 | $0.588 ↓ | Compare | |
| 2026-05-22 00:03 Suite changed | 7.7 | 10.0 | $0.650 | Compare | |
| 2026-04-11 01:44 First recorded run | 8.1 | N/A | $0.528 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-07-16 22:21 · New test added | 66/66 attempts | 7.1 | 8.5 | 10.0 | 14/22 | 4 | 487,218 | 124,771 | $1.046 | 64.16s |
| 2026-05-22 00:03 · Suite changed | 60/60 attempts | 7.7 | 8.8 | 10.0 | 13/20 | 3 | 238,285 | 0 | $0.650 | 39.29s |
| Difference | — | -0.5 | -0.3 | 0.0 | +1 | +1 | +248933 | +124771 | +$0.397 | +24870ms |
Benchmark coverage differs: 66/66 attempts (Target: 3 repeats per test) versus 60/60 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.
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price |
|---|---|---|
| 2026-06-04 15:40 | $0.260 / 1M | $2.080 / 1M |
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Qwen3.5-122B-A10BmediumvsMuse Glimmer 30BmediumQwen3.5-122B-A10BmediumvsMuse Glimmer 30BlowQwen3.5-122B-A10BmediumvsQwen3.7 FlashlowQwen3.5-122B-A10BmediumvsStep 3.7 FlashlowQwen3.5-122B-A10BmediumvsQwen3.5 Plus 2026-04-20mediumQwen3.5-122B-A10BmediumvsSolar Pro 4highQwen3.5-122B-A10BmediumvsMuse Glimmer 30BhighQwen3.5-122B-A10BmediumvsGrok 4.3mediumQwen3.5-122B-A10BmediumvsKAT-Coder-Pro V2.5highQwen3.5-122B-A10BmediumvsGPT-5.6 Solnone
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 10.0 | 10.0 | |
| Coding | 6.0 | 7.2 | |
| Combined | 6.4 | 5.8 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 2.9 | 7.2 | |
| General Intelligence | 3.4 | 2.2 | |
| Instructions following | 10.0 | 10.0 | |
| Puzzle Solving | 10.0 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |