Alibaba · model passport
Qwen3 5 Max Preview
qwen3-5-max-preview- Cloud only
- Proprietary licence
- Released 2026-10-15(first seen on LMArena)
- Overall · LMArena
- 1,464#50 of 396
- Best percentile
- 91.4Instruction following
- Cohort standing
- 74.5median 60.6
What the data says
Benchmarked on 5 of 27 tracked axes. Every figure below is the model's own published result on that board.
Strongest axes
- 91.4 pct — Instruction following (1,467)
- 89.9 pct — Hard prompts (1,491)
- 89 pct — Factuality Arena (1,474)
Uneven: 3.8 percentile points between its best and worst axis — 91.4 pct on Instruction following versus 87.6 pct on Overall.
- Instruction following91.4 pct1,467Verify →
- Hard prompts89.9 pct1,491Verify →
- Factuality Arena89 pct1,474Verify →
- Coding88.5 pct1,513Verify →
- Overall87.6 pct1,464Verify →
- WebDev ArenaNot benchmarked
- Vision ArenaNot benchmarked
- Search ArenaNot benchmarked
- Document ArenaNot benchmarked
- Agent ArenaNot benchmarked
- GPQA DiamondNot benchmarked
- AIME (math)Not benchmarked
- FrontierMathNot benchmarked
- SimpleQA VerifiedNot benchmarked
- ARC-AGI-2Not benchmarked
- Humanity's Last ExamNot benchmarked
- SimpleBenchNot benchmarked
- LiveBenchNot benchmarked
- BFCL v4 (function calling)Not benchmarked
- SWE-bench Verified (live board)Not benchmarked
- Terminal-Bench 4.0Not benchmarked
- MMLU-Pro (Artificial Analysis)Not benchmarked
- LiveCodeBench (Artificial Analysis)Not benchmarked
- IFBench (Artificial Analysis)Not benchmarked
- HHEM Hallucination (Vectara)Not benchmarked
- SWE-bench VerifiedNot benchmarked
- Terminal-BenchNot benchmarked
Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.
qwen3.5-max-preview stands at 74.5 (raw mean 89.3) — measured on 5 of 27 axes.
qwen3.5-max-preview stands at 74.5 versus a cohort median of 60.6 across 169 models released within 180 days — above the peer median.
qwen3.5-max-preview scores at percentile 91.4 on Instruction following.
qwen3.5-max-preview scores at percentile 89.9 on Hard prompts.
qwen3.5-max-preview ranks between #33 and #77 across 5 built-in weightings — best under "Conversation-first", worst under "All-rounder".
Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →