Qwen3-VL-235B-A22B-Thinking: benchmark scores, price and ranking

Qwen3-VL-235B-A22B-Thinking from Qwen ranks #138 of 827 LLMs on the LLMs Tiger aggregate benchmark score (51.6), based on 1 benchmark results captured up to 2026-11-18.

Organisation
Qwen
Type
Open-weight / local model
Open weights
Yes
Cheapest API price
$0.400 in / $4.00 out per million tokens (via dashscope, observed 2026-11-18T16:47Z)
Aggregate rank
#138 of 827 (score 51.6)

Across the 1 benchmark where at least ten models are scored, Qwen3-VL-235B-A22B-Thinking is in the top 10% on 0 and in the top half on 1.

Its cheapest listed input price, $0.400 per million tokens, is lower than that of 53% of the 443 models with a listed price.

Qwen3-VL-235B-A22B-Thinking benchmark results

Qwen3-VL-235B-A22B-Thinking benchmark scores, ranked against all models measured on each benchmark
BenchmarkScoreRankSourceCaptured
MMLU-Pro83.8%#24 of 158HuggingFace MMLU-Pro leaderboard2026-11-18

About Qwen3-VL-235B-A22B-Thinking

Qwen3-VL-235B-A22B-Thinking is an open-weight model that can run on your own hardware from Qwen. The cheapest API listing we track charges $0.400 per million input tokens and $4.00 per million output tokens, through dashscope. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.

Where Qwen3-VL-235B-A22B-Thinking stands

On our aggregate score, Qwen3-VL-235B-A22B-Thinking is #138 of 827 ranked models, in the top quarter. Its score is 51.6; the scale is centred on 50, so it sits 1.6 points above the typical model. That beats 83% of the ranked field. Among the 25 ranked Qwen models it is #5. The next one up is Qwen3.8-Flash-Next at 51.7. The next one down is Qwen3-4B-Thinking-2507 at 49.3.

Qwen3-VL-235B-A22B-Thinking, benchmark by benchmark

MMLU-Pro puts Qwen3-VL-235B-A22B-Thinking at 83.8%, #24 of 158. That beats 85% of the models tested, but 6.0 points short of Intern-S2-Preview-397B (89.8%). The results either side are K-EXAONE-236B-A23B (83.8%) and NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (83.7%). It covers 57-subject knowledge + reasoning. The board median is 58.1%, so Qwen3-VL-235B-A22B-Thinking is 25.7 points above it. Source: HuggingFace MMLU-Pro leaderboard, captured 2026-11-18.

Price and value

The median input price across the 443 priced models is $0.482 per million tokens, so Qwen3-VL-235B-A22B-Thinking costs less than the typical listing. Models that score within 1.5 points or better and cost less: GLM-5.2 (high) ($0.0070, 51.6), Qwen3.7 Flash ($0.030, 50.2), DeepSeek V4.1 Flash 1017 (max) ($0.036, 55.5). Similar scores cost more on Hy4-preview ($0.417) and Kimi K2.5 (Fireworks) ($0.450).

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

More from Qwen

Compare it on the live leaderboard → · How the aggregate score works