Qwen3.5 Plus: benchmark scores, price and ranking
Qwen3.5 Plus from Alibaba ranks #253 of 743 LLMs on the LLMs Tiger aggregate benchmark score (49.6), based on 12 benchmark results captured up to 2026-10-13.
- Organisation
- Alibaba
- Type
- Frontier model
- Open weights
- No
- Released
- 2026-02-16 (source: epoch)
- Aggregate rank
- #253 of 743 (score 49.6)
Relative to other models, Qwen3.5 Plus is strongest on OTIS Mock AIME (#54 of 189) and weakest on Vending-Bench 2 (#19 of 19).
Across the 11 benchmarks where at least ten models are scored, Qwen3.5 Plus is in the top 10% on 0 and in the top half on 6.
Qwen3.5 Plus benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| OTIS Mock AIME | 86.7% | #54 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 84.8% | #83 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Chess Puzzles | 22.0% | #38 of 122 | Epoch AI Benchmarking Hub | 2026-10-13 |
| CL-bench | 19.8% | #5 of 16 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DTBench | 80.5% | #51 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMCA | 36.4% | #42 of 108 | Epoch AI Benchmarking Hub | 2026-10-13 |
| CL-bench Life | 12.4% | #4 of 9 | Epoch AI Benchmarking Hub | 2026-10-13 |
| WebDev Arena | 1,399 | #36 of 67 | Epoch AI Benchmarking Hub | 2026-10-13 |
| ALE-Bench | 622 | #52 of 79 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Mystery Games | 17.0% | #40 of 59 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SimpleQA Verified | 25.4% | #53 of 69 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Vending-Bench 2 | $1 | #19 of 19 | Epoch AI Benchmarking Hub | 2026-10-13 |
About Qwen3.5 Plus
Qwen3.5 Plus is a frontier model from Alibaba. It was released on 2026-02-16, according to Epoch AI. No API price is listed for it yet. We hold 12 benchmark results for it across 4 areas, and none is in the top tenth of its board.
Where Qwen3.5 Plus stands
On our aggregate score, Qwen3.5 Plus is #253 of 743 ranked models, around the middle of the table. Its score is 49.6; the scale is centred on 50, so it sits 0.4 points below the typical model. That beats 66% of the ranked field. Among the 74 ranked Alibaba models it is #22. The next one up is qwen3.5-4b (none) at 49.6. The next one down is Qwen2.5-Coder-7B-Instruct at 49.5.
Qwen3.5 Plus, benchmark by benchmark
OTIS Mock AIME puts Qwen3.5 Plus at 86.7%, #54 of 189. That beats 71% of the models tested, but 13.3 points short of Claude Fable 5.1 (max) (100.0%). The results either side are Qwen3-235B-A22B-Thinking-2507 (86.7%) and Qwen3.6 35B-A3B (86.7%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so Qwen3.5 Plus is 28.9 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On GPQA Diamond, Qwen3.5 Plus reaches 84.8%. It ranks #83 of 275, ahead of 70% of the field, and 10.9 points behind GPT-6 Astra (max) at 95.8%. The results either side are Gemini 2.5 Pro Preview (Jun 2025) (84.8%) and Kimi K2 Thinking (84.5%). It covers expert-level science questions. The board median is 71.7%, so Qwen3.5 Plus is 13.1 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen3.5 Plus manages 22.0% on Chess Puzzles, good for #38 of 122. GPT-6 Astra (max) leads at 72.0%, 50.0 points further up, and 69% of models sit below. The results either side are Qwen3.7 Flash (23.0%) and Qwen3.6 27B (22.0%). It covers chess tactics puzzles. The board median is 12.5%, so Qwen3.5 Plus is 9.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
CL-bench puts Qwen3.5 Plus at 19.8%, #5 of 16. That beats 69% of the models tested, but 8.1 points short of GPT-5.4 (xhigh) (27.9%). The results either side are Qwen 3.6 Plus (2026-04-02) (20.3%) and Kimi K2.5 (19.3%). It covers learning new rules from context. The board median is 17.7%, so Qwen3.5 Plus is 2.1 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On DTBench, Qwen3.5 Plus reaches 80.5%. It ranks #51 of 146, ahead of 65% of the field, and 18.4 points behind Claude Opus 5.5 (max) at 98.9%. The results either side are GPT-5 mini (high) (80.5%) and GPT-5.4 nano (xhigh) (80.3%). It covers dynamic tool-use benchmark. The board median is 68.8%, so Qwen3.5 Plus is 11.7 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen3.5 Plus manages 36.4% on LMCA, good for #42 of 108. Claude Opus 5.5 (max) leads at 68.2%, 31.9 points further up, and 61% of models sit below. The results either side are GPT-5.4 nano (xhigh) (36.9%) and DeepSeek v4 Flash (max) (35.9%). It covers language-model capability assessment. The board median is 29.2%, so Qwen3.5 Plus is 7.1 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen3.5 Plus lands below the middle on ALE-Bench: 622, #52 of 79, with 65% of the field scoring higher. GPT-6 Astra (max) leads at 2,951; the closest result above is MiniMax-M2.1 at 624. It covers AtCoder heuristic-optimisation contests (performance rating). The board median is 764, so Qwen3.5 Plus is 142 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen3.5 Plus lands below the middle on Mystery Games: 17.0%, #40 of 59, with 66% of the field scoring higher. GPT-6 Astra (max) leads at 84.0%; the closest result above is Qwen3.5 397B-A17B at 18.0%. It covers deductive reasoning puzzles. The board median is 23.0%, so Qwen3.5 Plus is 6.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen3.5 Plus lands below the middle on SimpleQA Verified: 25.4%, #53 of 69, with 75% of the field scoring higher. gemini-4-argon-high leads at 76.0%; the closest result above is GPT-4o (Aug 2024) at 26.0%. It covers short factual questions. The board median is 41.0%, so Qwen3.5 Plus is 15.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Vending-Bench 2 is a weak spot. Qwen3.5 Plus scores $1, #19 of 19, behind 95% of the models measured. The leader, Kimi K2.6, reaches $6,205. It covers running a vending business for a year (final money, $). The board median is $2,377, so Qwen3.5 Plus is 2,376 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
The full table above also lists the other 2 results, including boards with fewer than ten models, where a rank says little.
Strengths and weaknesses
Software engineering: uneven, ahead of 40% of the field on average across 2 benchmarks. Its best board here is WebDev Arena (#36 of 67) and its weakest is ALE-Bench (#52 of 79). Reasoning, maths and science: solid, ahead of 71% of the field on average across 2 benchmarks. Its best board here is OTIS Mock AIME (#54 of 189) and its weakest is GPQA Diamond (#83 of 275). General knowledge and chat: uneven, ahead of 42% of the field on average across 6 benchmarks. Its best board here is Chess Puzzles (#38 of 122) and its weakest is Vending-Bench 2 (#19 of 19).
Release history
The Alibaba model released before it was Qwen3.5 397B-A17B on 2026-02-13, which scores 51.1. The next one was Qwen3.5 27B on 2026-02-24, at 49.3.
Reading these numbers
The 12 scores on this page come from 1 source: Epoch AI Benchmarking Hub (12). No official leaderboard supplied any of them, so treat them as third-party measurements.
Models ranked nearby
- #250 Grok-2 (49.6)
- #251 ollama/qwen2.5:32b-instruct-q8_0 (49.6)
- #252 qwen3.5-4b (none) (49.6)
- #254 Mistral-Large-Instruct-2411 (49.6)
- #255 DeepSeek v4 Flash (max) (49.6)
- #256 gpt-4o-2024-11-20 (49.6)
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