Skip to content
aiqbench

Alibaba · model passport

Qwen2 5 Coder 32b Instruct

qwen2-5-coder-32b-instruct
  • Open weights
  • Apache 2.0 licence
  • 32.8B params
  • Released 2024-11-11(curated)
6/27axes covered
Overall · LMArena
1,271#291 of 396
Best percentile
35.4LiveBench
Cohort standing
36.6median 40.7

What the data says

Benchmarked on 6 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 12.3 percentile points between its best and worst axis — 35.4 pct on LiveBench versus 23.1 pct on SWE-bench Verified (live board).

  • LiveBench35.4 pct46.2%Verify →
  • Coding33.5 pct1,342Verify →
  • Hard prompts31.3 pct1,303Verify →
  • Instruction following29 pct1,264Verify →
  • Overall26.8 pct1,271Verify →
  • SWE-bench Verified (live board)23.1 pct38.0%Verify →
  • 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
  • BFCL v4 (function calling)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

RepositoryQwen/Qwen2.5-Coder-32B-Instruct
Parameters32.8B
ArchitectureQwen2ForCausalLM
LicenceApache 2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Qwen/Qwen2.5-Coder-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.

  • qwen2.5-coder-32b-instruct stands at 36.6 (raw mean 29.8) — measured on 6 of 27 axes.

    standingtemplateVerify →

  • qwen2.5-coder-32b-instruct stands at 36.6 versus a cohort median of 40.7 across 136 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 →