Skip to content
aiqbench

Cohere · model passport

C4ai Aya Expanse 32b

c4ai-aya-expanse-32b
  • Open weights
  • CC-BY-NC-4.0 licence
  • Released 2024-10-24(curated)
5/27axes covered
Overall · LMArena
1,267#292 of 396
Best percentile
35.2HHEM Hallucination (Vectara)
Cohort standing
36.2median 39.9

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: 10.1 percentile points between its best and worst axis — 35.2 pct on HHEM Hallucination (Vectara) versus 25.1 pct on Coding.

  • HHEM Hallucination (Vectara)35.2 pct89.1%Verify →
  • Overall26.5 pct1,267Verify →
  • Instruction following26.3 pct1,249Verify →
  • Hard prompts26.3 pct1,272Verify →
  • Coding25.1 pct1,292Verify →
  • 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
  • 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.

  • c4ai-aya-expanse-32b stands at 36.2 (raw mean 27.9) — measured on 5 of 27 axes.

    standingtemplateVerify →

  • c4ai-aya-expanse-32b stands at 36.2 versus a cohort median of 39.9 across 133 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 →