Skip to content
aiqbench

Microsoft · model passport

Phi 3 Medium 4k Instruct

phi-3-medium-4k-instruct
  • Open weights
  • MIT licence
  • 14.0B params
  • Released 2024-05-21(curated)
5/27axes covered
Overall · LMArena
1,198#328 of 396
Best percentile
17.4Overall
Cohort standing
29.0median 34.8

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: 2.3 percentile points between its best and worst axis — 17.4 pct on Overall versus 15.1 pct on Coding.

  • Overall17.4 pct1,198Verify →
  • Instruction following16.9 pct1,178Verify →
  • Hard prompts16.9 pct1,213Verify →
  • LiveBench15.8 pct31.0%Verify →
  • Coding15.1 pct1,231Verify →
  • 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
  • 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

Repositorymicrosoft/Phi-3-medium-4k-instruct
Parameters14.0B
ArchitecturePhi3ForCausalLM
LicenceMIT

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "microsoft/Phi-3-medium-4k-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.

  • phi-3-medium-4k-instruct stands at 29 (raw mean 16.4) — measured on 5 of 27 axes.

    standingtemplateVerify →

  • phi-3-medium-4k-instruct stands at 29 versus a cohort median of 34.8 across 120 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 →