Qwen3-30B-A3B-Base: benchmark scores, price and ranking

Qwen3-30B-A3B-Base from Qwen ranks #326 of 743 LLMs on the LLMs Tiger aggregate benchmark score (48.7), based on 1 benchmark results captured up to 2026-10-13.

Organisation: Qwen
Type: Open-weight / local model
Open weights: Yes
Aggregate rank: #326 of 743 (score 48.7)

Across the 1 benchmark where at least ten models are scored, Qwen3-30B-A3B-Base is in the top 10% on 0 and in the top half on 1.

Qwen3-30B-A3B-Base benchmark results

Qwen3-30B-A3B-Base benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
MMLU-Pro	61.7%	#56 of 136	HuggingFace MMLU-Pro leaderboard	2026-10-13

About Qwen3-30B-A3B-Base

Qwen3-30B-A3B-Base is an open-weight model that can run on your own hardware from Qwen. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.

Where Qwen3-30B-A3B-Base stands

On our aggregate score, Qwen3-30B-A3B-Base is #326 of 743 ranked models, around the middle of the table. Its score is 48.7; the scale is centred on 50, so it sits 1.3 points below the typical model. That beats 56% of the ranked field. Among the 23 ranked Qwen models it is #8. The next one up is Qwen2.5-14B at 49.0. The next one down is qwen3-4b-instruct-2507 at 48.7.

Qwen3-30B-A3B-Base, benchmark by benchmark

MMLU-Pro puts Qwen3-30B-A3B-Base at 61.7%, #56 of 136. That beats 59% of the models tested, but 26.4 points short of Darwin-180B-RSI (88.1%). The results either side are Qwen2.5-14B (63.7%) and Llama 3.1-405B (61.6%). It covers 57-subject knowledge + reasoning. The board median is 55.3%, so Qwen3-30B-A3B-Base is 6.4 points above it. Source: HuggingFace MMLU-Pro leaderboard, captured 2026-10-13.

Reading these numbers

The 1 score on this page comes from 1 source: HuggingFace MMLU-Pro leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 1 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#323 glm-5.2-max (48.8)
#324 Opus 4.5 (Thinking, 16K) (48.8)
#325 gemini-2.5-flash-lite-preview-06-17_16K (48.7)
#327 GLM-4.5-Air (48.7)
#328 GPT-5.1 Codex Mini (48.7)
#329 Amazon.nova Premier v1:0 (48.7)