Qwen3-235b-a22b Instruct (25/07): benchmark scores, price and ranking
Qwen3-235b-a22b Instruct (25/07) from Alibaba ranks #425 of 743 LLMs on the LLMs Tiger aggregate benchmark score (47.5), based on 1 benchmark results captured up to 2026-10-13.
- Organisation
- Alibaba
- Type
- Open-weight / local model
- Open weights
- Yes
- Aggregate rank
- #425 of 743 (score 47.5)
Across the 1 benchmark where at least ten models are scored, Qwen3-235b-a22b Instruct (25/07) is in the top 10% on 0 and in the top half on 0.
Qwen3-235b-a22b Instruct (25/07) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| ARC-AGI-2 | 1.2% | #72 of 87 | ARC Prize official leaderboard | 2026-10-13 |
About Qwen3-235b-a22b Instruct (25/07)
Qwen3-235b-a22b Instruct (25/07) is an open-weight model that can run on your own hardware from Alibaba. 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 Qwen3-235b-a22b Instruct (25/07) stands
On our aggregate score, Qwen3-235b-a22b Instruct (25/07) is #425 of 743 ranked models, around the middle of the table. Its score is 47.5; the scale is centred on 50, so it sits 2.5 points below the typical model. That beats 43% of the ranked field. Among the 74 ranked Alibaba models it is #43. The next one up is Qwen2-VL-72B-Instruct at 47.6. The next one down is qwen3-30b-a3b-thinking-2507 at 47.2.
Qwen3-235b-a22b Instruct (25/07), benchmark by benchmark
ARC-AGI-2 is a weak spot. Qwen3-235b-a22b Instruct (25/07) scores 1.2%, #72 of 87, behind 82% of the models measured. The leader, GPT-6 Astra (max), reaches 95.0%. It covers abstract reasoning, ARC Prize public eval set. The board median is 22.8%, so Qwen3-235b-a22b Instruct (25/07) is 21.5 points below it. Source: ARC Prize official leaderboard, captured 2026-10-13.
Reading these numbers
The 1 score on this page comes from 1 source: ARC Prize official leaderboard (1). 1 of them come from an official leaderboard and 0 from datasets or third-party runs. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #422 Grok Build + Grok 4.5 (47.5)
- #423 Meta-Llama-3-70B (47.5)
- #424 Codex Mini (Latest) (47.5)
- #426 Deepseek R1 (05/28) (47.5)
- #427 Gemini 1.5 Pro (47.5)
- #428 GPT-4.5 (47.5)
More from Alibaba
- Qwen 3.6 Max (Preview) (#25, 54.1)
- Qwen3.8 Max (xhigh) (#37, 53.2)
- Qwen3.7 Max (#71, 52.3)
- ollama/qwen2.5-coder:32b (#93, 51.9)
- Qwen3 235B A22B diff, no think, Alibaba API (#122, 51.5)
- Qwen2.5-Coder-14B-Instruct (#135, 51.3)
Compare it on the live leaderboard → · How the aggregate score works