Skip to content
aiqbench

Snowflake · model passport

Snowflake Arctic Instruct

snowflake-arctic-instruct
  • Open weights
  • Apache 2.0 licence
  • 478.6B params
  • Released 2024-04-24(curated)
5/27axes covered
Overall · LMArena
1,180#340 of 396
Best percentile
95.2HHEM Hallucination (Vectara)
Cohort standing
37.8median 32.9

What the data says

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

Strongest axes

  • 95.2 pct — HHEM Hallucination (Vectara) (95.7%)

Weakest axes

  • 13.9 pct — Instruction following (1,154)
  • 14.4 pct — Overall (1,180)
  • 14.6 pct — Hard prompts (1,187)

Uneven: 81.3 percentile points between its best and worst axis — 95.2 pct on HHEM Hallucination (Vectara) versus 13.9 pct on Instruction following.

  • HHEM Hallucination (Vectara)95.2 pct95.7%Verify →
  • Coding14.6 pct1,225Verify →
  • Hard prompts14.6 pct1,187Verify →
  • Overall14.4 pct1,180Verify →
  • Instruction following13.9 pct1,154Verify →
  • 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.

How to run it

Run it yourself

RepositorySnowflake/snowflake-arctic-instruct
Parameters478.6B
ArchitectureArcticForCausalLM
LicenceApache 2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Snowflake/snowflake-arctic-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.

  • snowflake-arctic-instruct stands at 37.8 (raw mean 30.5) — measured on 5 of 27 axes.

    standingtemplateVerify →

  • snowflake-arctic-instruct stands at 37.8 versus a cohort median of 32.9 across 120 models released within 180 days — above 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 →