Skip to content
aiqbench

Alibaba · model passport

Qwen2 5 Max

qwen2-5-max
  • Cloud only
  • Proprietary licence
  • Released 2025-01-29(curated)
7/27axes covered
Overall · LMArena
1,374#180 of 396
Best percentile
61.5LiveBench
Cohort standing
52.6median 43.0

What the data says

Benchmarked on 7 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 14.9 percentile points between its best and worst axis — 61.5 pct on LiveBench versus 46.6 pct on LiveCodeBench (Artificial Analysis).

  • LiveBench61.5 pct60.0%Verify →
  • Overall54.8 pct1,374Verify →
  • MMLU-Pro (Artificial Analysis)54.7 pct76.2%Verify →
  • Hard prompts54 pct1,385Verify →
  • Instruction following53.5 pct1,356Verify →
  • Coding50.9 pct1,402Verify →
  • LiveCodeBench (Artificial Analysis)46.6 pct35.9%Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality 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
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not 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.

  • qwen2.5-max stands at 52.6 (raw mean 53.7) — measured on 7 of 27 axes.

    standingtemplateVerify →

  • qwen2.5-max stands at 52.6 versus a cohort median of 43 across 139 models released within 180 days — above the peer median.

    cohorttemplateVerify →

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 →