Skip to content
aiqbench

Tencent · model passport

Hunyuan Vision 1 5 Thinking

hunyuan-vision-1-5-thinking
  • Cloud only
  • Proprietary licence
  • Released 2026-01-09(first seen on LMArena)
5/27axes covered
Overall · LMArena
1,394#157 of 396
Best percentile
64.6Instruction following
Cohort standing
53.8median 55.5

What the data says

Benchmarked on 5 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 31.9 percentile points between its best and worst axis — 64.6 pct on Instruction following versus 32.7 pct on Vision Arena.

  • Instruction following64.6 pct1,395Verify →
  • Hard prompts62.6 pct1,419Verify →
  • Overall60.6 pct1,394Verify →
  • Coding59.8 pct1,436Verify →
  • Vision Arena32.7 pct1,155Verify →
  • WebDev 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.

  • hunyuan-vision-1.5-thinking stands at 53.8 (raw mean 56.1) — measured on 5 of 27 axes.

    standingtemplateVerify →

  • hunyuan-vision-1.5-thinking stands at 53.8 versus a cohort median of 55.5 across 116 models released within 180 days — below 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 →