Qwen 3.6 Flash (2026-04-16): benchmark scores, price and ranking
Qwen 3.6 Flash (2026-04-16) from Alibaba ranks #457 of 743 LLMs on the LLMs Tiger aggregate benchmark score (47.2), based on 10 benchmark results captured up to 2026-10-13.
- Organisation
- Alibaba
- Type
- Fast / low-cost (flash) model
- Open weights
- No
- Released
- 2026-04-16 (source: name)
- Aggregate rank
- #457 of 743 (score 47.2)
Relative to other models, Qwen 3.6 Flash (2026-04-16) is strongest on OTIS Mock AIME (#57 of 189) and weakest on ALE-Bench (#69 of 79).
Across the 10 benchmarks where at least ten models are scored, Qwen 3.6 Flash (2026-04-16) is in the top 10% on 0 and in the top half on 5.
Qwen 3.6 Flash (2026-04-16) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| OTIS Mock AIME | 84.4% | #57 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 83.3% | #94 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Chess Puzzles | 20.0% | #47 of 122 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DTBench | 77.1% | #62 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMCA | 31.0% | #49 of 108 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SimpleBench | 35.2% | #38 of 61 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Mystery Games | 18.0% | #38 of 59 | Epoch AI Benchmarking Hub | 2026-10-13 |
| FrontierMath T1-3 | 22.5% | #53 of 68 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SimpleQA Verified | 15.9% | #60 of 69 | Epoch AI Benchmarking Hub | 2026-10-13 |
| ALE-Bench | 326 | #69 of 79 | Epoch AI Benchmarking Hub | 2026-10-13 |
About Qwen 3.6 Flash (2026-04-16)
Qwen 3.6 Flash (2026-04-16) is a smaller, lower-cost model from Alibaba. It was released on 2026-04-16, according to the model's own name. No API price is listed for it yet. We hold 10 benchmark results for it across 4 areas, and none is in the top tenth of its board.
Where Qwen 3.6 Flash (2026-04-16) stands
On our aggregate score, Qwen 3.6 Flash (2026-04-16) is #457 of 743 ranked models, in the lower half. Its score is 47.2; the scale is centred on 50, so it sits 2.8 points below the typical model. That beats 38% of the ranked field. Among the 74 ranked Alibaba models it is #45. The next one up is qwen3-30b-a3b-thinking-2507 at 47.2. The next one down is qwen3.7-max-20260517 at 47.2.
Qwen 3.6 Flash (2026-04-16), benchmark by benchmark
OTIS Mock AIME puts Qwen 3.6 Flash (2026-04-16) at 84.4%, #57 of 189. That beats 70% of the models tested, but 15.6 points short of Claude Fable 5.1 (max) (100.0%). The results either side are Qwen3.7 Flash (86.7%) and Qwen3.5 Flash (84.4%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so Qwen 3.6 Flash (2026-04-16) is 26.7 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On GPQA Diamond, Qwen 3.6 Flash (2026-04-16) reaches 83.3%. It ranks #94 of 275, ahead of 66% of the field, and 12.4 points behind GPT-6 Astra (max) at 95.8%. The results either side are MiMo-V2-Flash (83.3%) and GPT-5.5 Instant (82.5%). It covers expert-level science questions. The board median is 71.7%, so Qwen 3.6 Flash (2026-04-16) is 11.6 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen 3.6 Flash (2026-04-16) manages 20.0% on Chess Puzzles, good for #47 of 122. GPT-6 Astra (max) leads at 72.0%, 52.0 points further up, and 61% of models sit below. The results either side are Kimi K2 Thinking Turbo (20.0%) and Qwen 3.6 Max (Preview) (20.0%). It covers chess tactics puzzles. The board median is 12.5%, so Qwen 3.6 Flash (2026-04-16) is 7.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
DTBench puts Qwen 3.6 Flash (2026-04-16) at 77.1%, #62 of 146. That beats 58% of the models tested, but 21.9 points short of Claude Opus 5.5 (max) (98.9%). The results either side are Claude Sonnet 4 (unknown thinking) (77.1%) and gemini-2.5-flash (76.5%). It covers dynamic tool-use benchmark. The board median is 68.8%, so Qwen 3.6 Flash (2026-04-16) is 8.3 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On LMCA, Qwen 3.6 Flash (2026-04-16) reaches 31.0%. It ranks #49 of 108, ahead of 55% of the field, and 37.2 points behind Claude Opus 5.5 (max) at 68.2%. The results either side are Qwen 3.6 Plus (2026-04-02) (33.1%) and Qwen3.6 35B-A3B (29.7%). It covers language-model capability assessment. The board median is 29.2%, so Qwen 3.6 Flash (2026-04-16) is 1.8 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen 3.6 Flash (2026-04-16) lands below the middle on SimpleBench: 35.2%, #38 of 61, with 61% of the field scoring higher. Claude Fable 5 (max) leads at 81.9%; the closest result above is grok-3 at 36.1%. It covers trick questions that test common sense. The board median is 41.4%, so Qwen 3.6 Flash (2026-04-16) is 6.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen 3.6 Flash (2026-04-16) lands below the middle on Mystery Games: 18.0%, #38 of 59, with 63% of the field scoring higher. GPT-6 Astra (max) leads at 84.0%; the closest result above is Kimi K2.6 at 18.0%. It covers deductive reasoning puzzles. The board median is 23.0%, so Qwen 3.6 Flash (2026-04-16) is 5.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen 3.6 Flash (2026-04-16) lands below the middle on FrontierMath T1-3: 22.5%, #53 of 68, with 76% of the field scoring higher. GPT-6 Astra (max) leads at 93.7%; the closest result above is GPT-5.5 Instant at 26.3%. It covers research-level maths, tiers 1-3. The board median is 55.6%, so Qwen 3.6 Flash (2026-04-16) is 33.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
SimpleQA Verified is a weak spot. Qwen 3.6 Flash (2026-04-16) scores 15.9%, #60 of 69, behind 86% of the models measured. The leader, gemini-4-argon-high, reaches 76.0%. It covers short factual questions. The board median is 41.0%, so Qwen 3.6 Flash (2026-04-16) is 25.1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
ALE-Bench is a weak spot. Qwen 3.6 Flash (2026-04-16) scores 326, #69 of 79, behind 86% of the models measured. The leader, GPT-6 Astra (max), reaches 2,951. It covers AtCoder heuristic-optimisation contests (performance rating). The board median is 764, so Qwen 3.6 Flash (2026-04-16) is 438 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: uneven, ahead of 49% of the field on average across 4 benchmarks. Its best board here is OTIS Mock AIME (#57 of 189) and its weakest is FrontierMath T1-3 (#53 of 68). General knowledge and chat: uneven, ahead of 41% of the field on average across 4 benchmarks. Its best board here is Chess Puzzles (#47 of 122) and its weakest is SimpleQA Verified (#60 of 69).
Release history
The Alibaba model released before it was Qwen3.6 35B-A3B on 2026-04-14, which scores 46.2. The next one was Qwen3.6 27B on 2026-04-22, at 44.9.
Reading these numbers
The 10 scores on this page come from 1 source: Epoch AI Benchmarking Hub (10). No official leaderboard supplied any of them, so treat them as third-party measurements.
Models ranked nearby
- #454 seed-2.1-pro-preview (47.2)
- #455 MAmmoTH2-8x7B-Plus (47.2)
- #456 qwen3-30b-a3b-thinking-2507 (47.2)
- #458 GPT-4o (47.2)
- #459 openhands-lm-32b-v0.1 (47.2)
- #460 qwen3.7-max-20260517 (47.2)
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