LLMs TigerLive LLM benchmarks

Qwen 3.6 Plus (2026-04-02): benchmark scores, price and ranking

Qwen 3.6 Plus (2026-04-02) from Alibaba ranks #212 of 743 LLMs on the LLMs Tiger aggregate benchmark score (50.1), based on 15 benchmark results captured up to 2026-10-13.

Organisation
Alibaba
Type
Frontier model
Open weights
No
Released
2026-04-02 (source: name)
Aggregate rank
#212 of 743 (score 50.1)

Relative to other models, Qwen 3.6 Plus (2026-04-02) is strongest on GPQA Diamond (#47 of 275) and weakest on Mystery Games (#45 of 59).

Across the 15 benchmarks where at least ten models are scored, Qwen 3.6 Plus (2026-04-02) is in the top 10% on 0 and in the top half on 10.

Qwen 3.6 Plus (2026-04-02) benchmark results

Qwen 3.6 Plus (2026-04-02) benchmark scores, ranked against all models measured on each benchmark
BenchmarkScoreRankSourceCaptured
GPQA Diamond88.4%#47 of 275Epoch AI Benchmarking Hub2026-10-13
OTIS Mock AIME93.3%#33 of 189Epoch AI Benchmarking Hub2026-10-13
Vending-Bench 2$5,115#4 of 19Epoch AI Benchmarking Hub2026-10-13
CL-bench20.3%#4 of 16Epoch AI Benchmarking Hub2026-10-13
DTBench81.9%#46 of 146Epoch AI Benchmarking Hub2026-10-13
WebDev Arena1,461#28 of 67Epoch AI Benchmarking Hub2026-10-13
Chess Puzzles17.0%#53 of 122Epoch AI Benchmarking Hub2026-10-13
SimpleQA Verified44.1%#30 of 69Epoch AI Benchmarking Hub2026-10-13
LMCA33.1%#48 of 108Epoch AI Benchmarking Hub2026-10-13
SWE-bench Verified57.9%#36 of 73Epoch AI Benchmarking Hub2026-10-13
CritPt2.9%#58 of 115Epoch AI Benchmarking Hub2026-10-13
SciCode40.7%#60 of 106Epoch AI Benchmarking Hub2026-10-13
ALE-Bench670#46 of 79Epoch AI Benchmarking Hub2026-10-13
FrontierMath T1-338.2%#44 of 68Epoch AI Benchmarking Hub2026-10-13
Mystery Games12.0%#45 of 59Epoch AI Benchmarking Hub2026-10-13

About Qwen 3.6 Plus (2026-04-02)

Qwen 3.6 Plus (2026-04-02) is a frontier model from Alibaba. It was released on 2026-04-02, according to the model's own name. No API price is listed for it yet. We hold 15 benchmark results for it across 4 areas, and none is in the top tenth of its board.

Where Qwen 3.6 Plus (2026-04-02) stands

On our aggregate score, Qwen 3.6 Plus (2026-04-02) is #212 of 743 ranked models, around the middle of the table. Its score is 50.1; the scale is centred on 50, so it sits 0.1 points above the typical model. That beats 71% of the ranked field. Among the 74 ranked Alibaba models it is #15. The next one up is ollama/qwen2.5-coder:14b at 50.1. The next one down is Qwen2.5-72B at 50.1.

Qwen 3.6 Plus (2026-04-02), benchmark by benchmark

GPQA Diamond puts Qwen 3.6 Plus (2026-04-02) at 88.4%, #47 of 275. That beats 83% of the models tested, but 7.4 points short of GPT-6 Astra (max) (95.8%). The results either side are Claude Opus 4.6 (max) (88.4%) and Ring-2.6-1T (88.3%). It covers expert-level science questions. The board median is 71.7%, so Qwen 3.6 Plus (2026-04-02) is 16.7 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On OTIS Mock AIME, Qwen 3.6 Plus (2026-04-02) reaches 93.3%. It ranks #33 of 189, ahead of 83% of the field, and 6.7 points behind Claude Fable 5.1 (max) at 100.0%. The results either side are grok-4.3 (high) (93.3%) and Qwen3.7 Plus (93.3%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so Qwen 3.6 Plus (2026-04-02) is 35.6 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen 3.6 Plus (2026-04-02) manages $5,115 on Vending-Bench 2, good for #4 of 19. Kimi K2.6 leads at $6,205, 1,090 points further up, and 79% of models sit below. The results either side are Gemini 3 Pro Preview ($5,478) and Kimi K2.7 Code ($5,083). It covers running a vending business for a year (final money, $). The board median is $2,377, so Qwen 3.6 Plus (2026-04-02) is 2,738 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

CL-bench puts Qwen 3.6 Plus (2026-04-02) at 20.3%, #4 of 16. That beats 75% of the models tested, but 7.6 points short of GPT-5.4 (xhigh) (27.9%). The results either side are grok-4-20 (22.2%) and Qwen3.5 Plus (19.8%). It covers learning new rules from context. The board median is 17.7%, so Qwen 3.6 Plus (2026-04-02) is 2.6 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On DTBench, Qwen 3.6 Plus (2026-04-02) reaches 81.9%. It ranks #46 of 146, ahead of 68% of the field, and 17.1 points behind Claude Opus 5.5 (max) at 98.9%. The results either side are Qwen3-Max-Instruct (82.1%) and Claude Opus 4 (81.6%). It covers dynamic tool-use benchmark. The board median is 68.8%, so Qwen 3.6 Plus (2026-04-02) is 13.1 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen 3.6 Plus (2026-04-02) manages 1,461 on WebDev Arena, good for #28 of 67. Claude Opus 5.5 (max) leads at 1,820, 360 points further up, and 58% of models sit below. The results either side are Kimi K2.7 Code (1,473) and Gemini 3 Pro Preview (1,439). It covers building web apps, crowd-voted (Elo). The board median is 1,433, so Qwen 3.6 Plus (2026-04-02) is 27 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen 3.6 Plus (2026-04-02) lands below the middle on SciCode: 40.7%, #60 of 106, with 56% of the field scoring higher. Claude Opus 5.5 (max) leads at 66.9%; the closest result above is Cogito v2.1 (671B) at 41.0%. It covers scientific research code. The board median is 44.3%, so Qwen 3.6 Plus (2026-04-02) is 3.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen 3.6 Plus (2026-04-02) lands below the middle on ALE-Bench: 670, #46 of 79, with 57% of the field scoring higher. GPT-6 Astra (max) leads at 2,951; the closest result above is claude-opus-4-1-20250805_16K at 675. It covers AtCoder heuristic-optimisation contests (performance rating). The board median is 764, so Qwen 3.6 Plus (2026-04-02) is 94 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen 3.6 Plus (2026-04-02) lands below the middle on FrontierMath T1-3: 38.2%, #44 of 68, with 63% of the field scoring higher. GPT-6 Astra (max) leads at 93.7%; the closest result above is grok-4.3 (high) at 42.8%. It covers research-level maths, tiers 1-3. The board median is 55.6%, so Qwen 3.6 Plus (2026-04-02) is 17.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen 3.6 Plus (2026-04-02) lands below the middle on Mystery Games: 12.0%, #45 of 59, with 75% of the field scoring higher. GPT-6 Astra (max) leads at 84.0%; the closest result above is gpt-4o-mini-2024-07-18 at 12.0%. It covers deductive reasoning puzzles. The board median is 23.0%, so Qwen 3.6 Plus (2026-04-02) is 11.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

The full table above also lists the other 5 results, including boards with fewer than ten models, where a rank says little.

Strengths and weaknesses

Software engineering: uneven, ahead of 49% of the field on average across 4 benchmarks. Its best board here is WebDev Arena (#28 of 67) and its weakest is ALE-Bench (#46 of 79). Reasoning, maths and science: solid, ahead of 63% of the field on average across 4 benchmarks. Its best board here is GPQA Diamond (#47 of 275) and its weakest is FrontierMath T1-3 (#44 of 68). General knowledge and chat: solid, ahead of 58% of the field on average across 6 benchmarks. Its best board here is Vending-Bench 2 (#4 of 19) and its weakest is Mystery Games (#45 of 59).

Release history

The Alibaba model released before it was Qwen3.5 Flash on 2026-02-25, which scores 46.4. The next one was qwen3.6-plus on 2026-04-02, at 46.6.

Reading these numbers

The 15 scores on this page come from 1 source: Epoch AI Benchmarking Hub (15). No official leaderboard supplied any of them, so treat them as third-party measurements.

Models ranked nearby

More from Alibaba

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