Skip to content
aiqbench

Allenai · model passport

Olmo 2 0325 32b Instruct

olmo-2-0325-32b-instruct
  • Open weights
  • Apache-2.0 licence
  • 32.2B params
  • Released 2025-03-25(curated)
4/27axes covered
Overall · LMArena
1,252#301 of 396
Best percentile
24.7Hard prompts
Cohort standing
35.1median 47.1

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: 1.4 percentile points between its best and worst axis — 24.7 pct on Hard prompts versus 23.3 pct on Coding.

  • Hard prompts24.7 pct1,262Verify →
  • Overall24.2 pct1,252Verify →
  • Instruction following23.5 pct1,229Verify →
  • Coding23.3 pct1,280Verify →
  • 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.

How to run it

Run it yourself

Repositoryallenai/OLMo-2-0325-32B-Instruct
Parameters32.2B
ArchitectureOlmo2ForCausalLM
LicenceApache-2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "allenai/OLMo-2-0325-32B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Ollama

We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →

Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • olmo-2-0325-32b-instruct stands at 35.1 (raw mean 23.9) — measured on 4 of 27 axes.

    standingtemplateVerify →

  • olmo-2-0325-32b-instruct stands at 35.1 versus a cohort median of 47.1 across 144 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 →