Benchfolio

Leaderboard / Model

Qwen 3.8 Max

Alibaba · Closed weights · Released Aug 2, 2026 · Price not listed

n/aOverall · not enough data

Score by job

Coding

Not enough data · 2 of 5 benchmarks

BenchmarkResultVariantz
DeepSWE57.5%qwen3.8-max_xhigh0.02
LMArena Coding1500 ratingqwen3.8-max0.46

Agents

Not enough data · 0 of 4 benchmarks

Reasoning

Not enough data · 1 of 4 benchmarks

BenchmarkResultVariantz
GPQA Diamond92.7%qwen3.8-max_xhigh0.45

Math

62 · rank 10 · 5 of 5 benchmarks

BenchmarkResultVariantz
FrontierMath Tiers 1–374.7%qwen3.8-max_xhigh0.47
FrontierMath Tier 446.3%qwen3.8-max_xhigh0.22
OTIS Mock AIME99.4%qwen3.8-max_xhigh0.95
ProofBench58.0%qwen3.8-max_unknown0.41
LMArena Math1500 ratingqwen3.8-max0.76

Writing

78 · rank 8 · 2 of 2 benchmarks

BenchmarkResultVariantz
LMArena Creative Writing1481 ratingqwen3.8-max0.91
LMArena Instruction Following1482 ratingqwen3.8-max0.67

Design

67 · rank 6 · 1 of 1 benchmarks

BenchmarkResultVariantz
LMArena WebDev1671 ratingqwen3.8-max1.12