Skip to content
aiqbench

Tencent · model passport

Hunyuan Standard

hunyuan-standard
  • Cloud only
  • Proprietary licence
  • Released 2025-02-10(from model name)
4/27axes covered
Overall · LMArena
1,311#253 of 395
Best percentile
36.2Overall
Cohort standing
40.7median 44.1

What the data says

Benchmarked on 4 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 4.4 percentile points between its best and worst axis — 36.2 pct on Overall versus 31.8 pct on Coding.

  • Overall36.2 pct1,311Verify →
  • Hard prompts33.9 pct1,310Verify →
  • Instruction following33.2 pct1,281Verify →
  • Coding31.8 pct1,331Verify →
  • 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
  • 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.

  • The hunyuan-standard-2025-02-10 model from tencent covers 4 of 27 axes with a composite shrinkage of 40.7 and a raw composite score of 33.8, without thin coverage.

    standingVerify →

  • The hunyuan-standard-2025-02-10 model from tencent has a standing of 40.7, which is below the cohort median standing of 44.1 across 148 models within an 180-day window.

    cohortVerify →

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 →