Compare Models

Qwen 3.6 Plus

Qwen 3.6 Plus is a model from Alibaba, released April 2, 2026. Its best result is #35 of 149 on LegalBench.

Release Date: Apr 2, 2026

Developer Alibaba  🇨🇳
Context Window 984k
Max Output Tokens 66k
Token Costs (in/out) $0.50/3.00
Weights Private
Input Modalities

Accuracy

50.56 %

Avg. Cost (In/Out)

$ 0.50 / $ 3.00

Latency

11 min 2 s

Vals Index
BenchmarksAccuracyRankings
Code Migration

11.10%

±1.31
60/74
EMB

32.87%

±2.81
59/72
Finance Agent (v2)

40.85%

±0.13
59/76
Legal Research Bench

14.90%

±2.48
61/75
MedCode

36.89%

±2.02
75/105
MedScribe

76.96%

±1.92
71/107
MortgageTax

67.97%

±0.91
21/98
SAGE

44.86%

±3.43
42/90
Tax Agent Bench

32.84%

±2.75
58/67
TaxEval v2

74.73%

±0.85
32/145
Vibe Code Bench v1.1

25.57%

±3.91
71/110
Harvey's Legal Agent Benchmark

1.25%

±0.83
53/76
GPQA Diamond

87.37%

±1.67
39/138
LiveCodeBench

85.95%

±0.98
25/143
LegalBench

84.23%

±0.42
35/149
MMLU Pro

87.67%

±0.32
24/138
MMMU Pro

84.16%

±0.88
27/93
ProgramBench

0.00%

±0.00
47/62
SWE-bench

73.40%

±1.98
52/88
Terminal-Bench 2.1

53.18%

±1.63
55/75
Proprietary BenchmarksAcademic BenchmarksIndustry Partners
Vals
Default Provider : Alibaba
Temperature: 0.7
Top P: Default
Top K: Default
Max Output Tokens: 65,536

Compared with

Qwen 3.6 Plus vs GPT 5.4 Nano 18 shared benchmarks Qwen 3.6 Plus vs Inkling 19 shared benchmarks Qwen 3.6 Plus vs Gemini 3.5 Flash Lite 19 shared benchmarks Qwen 3.6 Plus vs GPT 5.4 Mini 16 shared benchmarks Qwen 3.6 Plus vs MiMo V2.5 18 shared benchmarks Qwen 3.6 Plus vs MiMo V2.5 Pro 15 shared benchmarks Qwen 3.6 Plus vs Gemini 3.1 Pro Preview (02/26) 19 shared benchmarks Qwen 3.6 Plus vs MiniMax-M3 18 shared benchmarks

Updates

Apr 10, 2026

We evaluated Qwen 3.6 Plus on our suite of benchmarks. Here are the key takeaways:

  • On MedCode and MedScribe, the model ranked 30/50 and 27/50 respectively, indicating room for improvement.
  • Qwen 3.6 Plus places #17 overall on Vals Index (58.8% accuracy), just above GPT-5.4 Mini and just below Qwen 3.5 Plus (#14, 59.1%).
  • The model performs well on knowledge benchmarks, placing #6 on MMLU Pro (87.7%) and #8 on MMMU (84.2%).
  • It lands in the top 15 on most other benchmarks, with notable results on Mortgage Tax (#9, 68.0%) and Finance Agent (#11, 54.6%).
  • Its weakest showing is on Case Law (v2), where it ranks #42 (51.4%).
  • On Vibe Code Bench, it scores 25.9%, placing #13 and demonstrating a ~10% improvement over Qwen 3.5 Plus (15.74%, ranked #18).

All evals were run via the Alibaba API.