Llama 4 Maverick vs Qwen3-235B-A22B

Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.

Llama 4 Maverick

Meta · Apr 2025

Meta's natively multimodal 400B MoE — the largest openly downloadable US-made model, served cheaply across many hosts.

Qwen3-235B-A22B

Alibaba (Qwen) · Jul 2025

69.0

The most popular open general-purpose Qwen: 235B MoE with hybrid thinking, a staple of the 2025 open-source ecosystem.

The verdict

Qwen3-235B-A22B wins 2 of the 2 benchmarks these models share, against 0 for Llama 4 Maverick. Qwen3-235B-A22B is about 1.1x cheaper per blended million tokens (3:1 input:output mix). Llama 4 Maverick also takes 1M of context versus 262K for Qwen3-235B-A22B.

Benchmark head-to-head 02

GPQA Diamond
69.8%81.1%
Llama 4 MaverickQwen3-235B-A22B
MMLU-Pro
80.5%84.4%
Llama 4 MaverickQwen3-235B-A22B

Specs & pricing

Llama 4 MaverickQwen3-235B-A22B
modhub Index69.0
Input price / 1M$0.27$0.22
Output price / 1M$0.85$0.88
Context window1M262K
Max output33K
Open weightsyes (Llama 4 Community License)yes (Apache 2.0)
Reasoning modelnoyes
Multimodal inputtext, imagetext
Knowledge cutoffAug 2024Apr 2025
ReleasedApr 2025Jul 2025
Example monthly cost*$3.98$3.52

* 10M input + 1.5M output tokens per month at list prices, no caching. Green = better value on that row.

Frequently asked questions

Which is better, Llama 4 Maverick or Qwen3-235B-A22B?
Qwen3-235B-A22B wins 2 of the 2 benchmarks these models share, against 0 for Llama 4 Maverick. Qwen3-235B-A22B is about 1.1x cheaper per blended million tokens (3:1 input:output mix). Llama 4 Maverick also takes 1M of context versus 262K for Qwen3-235B-A22B.
Which is cheaper, Llama 4 Maverick or Qwen3-235B-A22B?
Llama 4 Maverick costs $0.27/$0.85 per million input/output tokens, while Qwen3-235B-A22B costs $0.22/$0.88. For a typical workload of 10M input and 1.5M output tokens per month, that's $3.98 versus $3.52.
Which model is better for coding, Llama 4 Maverick or Qwen3-235B-A22B?
We don't yet track SWE-bench Verified results for both models; check their individual pages for coding-related scores.

More comparisons