Qwen3.5 9B: benchmark scores, price and ranking
Qwen3.5 9B from Alibaba ranks #618 of 743 LLMs on the LLMs Tiger aggregate benchmark score (44.9), based on 9 benchmark results captured up to 2026-10-13.
- Organisation
- Alibaba
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2026-02-24 (source: epoch)
- Cheapest API price
- $0.100 in / $0.150 out per million tokens (via deepinfra, observed 2026-10-13T19:47Z)
- Aggregate rank
- #618 of 743 (score 44.9)
Relative to other models, Qwen3.5 9B is strongest on Epoch ECI (#54 of 204) and weakest on Terminal-Bench 2.0 (#28 of 28).
Across the 9 benchmarks where at least ten models are scored, Qwen3.5 9B is in the top 10% on 0 and in the top half on 4.
Its cheapest listed input price, $0.100 per million tokens, is lower than that of 79% of the 427 models with a listed price.
Qwen3.5 9B benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Epoch ECI | 139 | #54 of 204 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 79.0% | #111 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DTBench | 71.2% | #70 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 61.7% | #92 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Chess Puzzles | 12.0% | #66 of 122 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMCA | 24.5% | #65 of 108 | Epoch AI Benchmarking Hub | 2026-10-13 |
| CritPt | 0.3% | #83 of 115 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SciCode | 27.5% | #92 of 106 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Terminal-Bench 2.0 | 9.2% | #28 of 28 | Epoch AI Benchmarking Hub | 2026-10-13 |
About Qwen3.5 9B
Qwen3.5 9B is an open-weight model that can run on your own hardware from Alibaba. It was released on 2026-02-24, according to Epoch AI. The cheapest API listing we track charges $0.100 per million input tokens and $0.150 per million output tokens, through deepinfra. We hold 9 benchmark results for it across 4 areas, and none is in the top tenth of its board.
Where Qwen3.5 9B stands
On our aggregate score, Qwen3.5 9B is #618 of 743 ranked models, in the lower half. Its score is 44.9; the scale is centred on 50, so it sits 5.1 points below the typical model. That beats 17% of the ranked field. Among the 74 ranked Alibaba models it is #68. The next one up is Qwen3.6 27B at 44.9. The next one down is qwen-turbo-2024-11-01 at 44.5.
Qwen3.5 9B, benchmark by benchmark
Epoch ECI puts Qwen3.5 9B at 139, #54 of 204. That beats 74% of the models tested, but 17 points short of Qwen 3.8 Max (156). The results either side are Qwen3-30B-A3B-Thinking (Jul 2025) (140) and qwen3-235b-a22b (139). It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so Qwen3.5 9B is 12 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On GPQA Diamond, Qwen3.5 9B reaches 79.0%. It ranks #111 of 275, ahead of 60% of the field, and 16.8 points behind GPT-6 Astra (max) at 95.8%. The results either side are K-EXAONE-236B-A23B (79.1%) and Claude Sonnet 4.6 (max) (78.8%). It covers expert-level science questions. The board median is 71.7%, so Qwen3.5 9B is 7.3 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen3.5 9B manages 71.2% on DTBench, good for #70 of 146. Claude Opus 5.5 (max) leads at 98.9%, 27.7 points further up, and 52% of models sit below. The results either side are Qwen3.6 35B-A3B (73.9%) and Mistral Small 4 (70.9%). It covers dynamic tool-use benchmark. The board median is 68.8%, so Qwen3.5 9B is 2.4 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
OTIS Mock AIME puts Qwen3.5 9B at 61.7%, #92 of 189. That beats 51% of the models tested, but 38.3 points short of Claude Fable 5.1 (max) (100.0%). The results either side are qwen3-30b-a3b-instruct-2507 (62.2%) and QwQ-32B (59.2%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so Qwen3.5 9B is 3.9 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen3.5 9B lands below the middle on Chess Puzzles: 12.0%, #66 of 122, with 53% of the field scoring higher. GPT-6 Astra (max) leads at 72.0%; the closest result above is Qwen3-235B-A22B-Thinking-2507 at 12.0%. It covers chess tactics puzzles. The board median is 12.5%, so Qwen3.5 9B is 0.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen3.5 9B lands below the middle on LMCA: 24.5%, #65 of 108, with 59% of the field scoring higher. Claude Opus 5.5 (max) leads at 68.2%; the closest result above is qwen3-235b-a22b at 25.0%. It covers language-model capability assessment. The board median is 29.2%, so Qwen3.5 9B is 4.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen3.5 9B lands below the middle on CritPt: 0.3%, #83 of 115, with 71% of the field scoring higher. GPT-5.6 Sol (max) leads at 32.3%; the closest result above is Qwen3-32B at 0.3%. It covers unpublished research-level physics problems. The board median is 2.9%, so Qwen3.5 9B is 2.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
SciCode is a weak spot. Qwen3.5 9B scores 27.5%, #92 of 106, behind 86% of the models measured. The leader, Claude Opus 5.5 (max), reaches 66.9%. It covers scientific research code. The board median is 44.3%, so Qwen3.5 9B is 16.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Terminal-Bench 2.0 is a weak spot. Qwen3.5 9B scores 9.2%, #28 of 28, behind 96% of the models measured. The leader, Gemini 3 Pro Preview, reaches 69.4%. It covers real terminal tasks (agent + model). The board median is 37.3%, so Qwen3.5 9B is 28.1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Software engineering: weak, ahead of 7% of the field on average across 2 benchmarks. Its best board here is SciCode (#92 of 106) and its weakest is Terminal-Bench 2.0 (#28 of 28). Reasoning, maths and science: uneven, ahead of 46% of the field on average across 3 benchmarks. Its best board here is GPQA Diamond (#111 of 275) and its weakest is CritPt (#83 of 115). General knowledge and chat: solid, ahead of 53% of the field on average across 3 benchmarks. Its best board here is Epoch ECI (#54 of 204) and its weakest is LMCA (#65 of 108).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so Qwen3.5 9B costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on MiMo-V2-Flash ($0.110) and qwen3-coder-next ($0.120).
Release history
The Alibaba model released before it was qwen3.5-4b (none) on 2026-02-24, which scores 49.6. The next one was Qwen3.5 Flash on 2026-02-25, at 46.4.
Reading these numbers
The 9 scores on this page come from 1 source: Epoch AI Benchmarking Hub (9). No official leaderboard supplied any of them, so treat them as third-party measurements.
Models ranked nearby
- #615 Qwen3.6 27B (44.9)
- #616 Nova 2.0 Pro Preview (unknown) (44.9)
- #617 internlm2-math-plus-7b (44.9)
- #619 granite-3.1-8b-base (44.9)
- #620 GPT-4.1 (44.9)
- #621 Llama-3.1-Tulu-3-70B-DPO (44.8)
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