Skip to content
aiqbench

Model passport

Zephyr Orpo 141b A35b V0 1

zephyr-orpo-141b-a35b-v0-1
  • Open weights
  • Apache 2.0 licence
  • Released 2024-04-11(curated)
4/27axes covered
Overall · LMArena
1,213#321 of 396
Best percentile
19.4Instruction following
Cohort standing
31.8median 32.9

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: 2.5 percentile points between its best and worst axis — 19.4 pct on Instruction following versus 16.9 pct on Coding.

  • Instruction following19.4 pct1,194Verify →
  • Overall19.2 pct1,213Verify →
  • Hard prompts17.4 pct1,216Verify →
  • Coding16.9 pct1,245Verify →
  • 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.

  • zephyr-orpo-141b-A35b-v0.1 stands at 31.8 (raw mean 18.2) — measured on 4 of 27 axes.

    standingtemplateVerify →

  • zephyr-orpo-141b-A35b-v0.1 stands at 31.8 versus a cohort median of 32.9 across 117 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 →