The Open-Source AI Stack
RSS
All models

Models · Compare

Qwen3.5 122B-A10B vs Claude Sonnet 4.6

Rows highlighted in warm gray are where the models differ. Numbers carry their as-of date and primary source.

Specs

Field A: Qwen3.5 122B-A10B B: Claude Sonnet 4.6
Released 2026-02-162026-02-17
Developer AlibabaAnthropic
Openness OpenProprietary
License Apache-2.0Proprietary
OSI-approved yesno
Data released nono
Training code nono
Architecture moeunknown
Total params 122B
Active params 10B
Experts
Context window 262K1.0M
Attention gqaunknown
Position enc. rope-yarnunknown
Pretraining tokens
Post-training sft, rlhfrlhf, constitutional
Training hardware
$/M input $3.00
$/M output $15.00
Output tok/sec 49

Benchmarks

Missing scores render as not reported; never inferred. Bold highlights the leader per benchmark.

General reasoning

GPQA-Diamond 79.9 2026-05-21

Code

SWE-Bench Verified 80.2 2026-02-17

Context · A

A mid-size Qwen3.5 mixture-of-experts: 122B total with about 10B active per token. The large footprint needs a high-capacity box, while the 10B active count keeps single-stream decode brisk; it is often run at IQ4_XS for long-context work.

Context · B

Mid-tier Sonnet refresh shipped February 17 2026 at the same $3 / $15 pricing as Sonnet 4.5, with a 1M context window in beta. Default model for Free and Pro plans on Claude.ai at launch. Anthropic reported Claude Code users preferred Sonnet 4.6 over Sonnet 4.5 roughly 70 percent of the time.

Qwen3.5 122B-A10B detail → · Claude Sonnet 4.6 detail →