Skip to content
aiqbench

01.AI · model passport

Yi 1 5 34b Chat

yi-1-5-34b-chat
  • Open weights
  • Apache-2.0 licence
  • 34.4B params
  • Released 2024-05-13(curated)
5/27axes covered
Overall · LMArena
1,213#322 of 396
Best percentile
19.2Hard prompts
Cohort standing
29.5median 34.5

What the data says

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

Weakest axes

  • 12.2 pct — GPQA Diamond (32.0%)

Uneven: 7 percentile points between its best and worst axis — 19.2 pct on Hard prompts versus 12.2 pct on GPQA Diamond.

  • Hard prompts19.2 pct1,226Verify →
  • Overall18.9 pct1,213Verify →
  • Instruction following18.2 pct1,188Verify →
  • Coding17.1 pct1,248Verify →
  • GPQA Diamond12.2 pct32.0%Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot 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

Repository01-ai/Yi-1.5-34B-Chat
Parameters34.4B
ArchitectureLlamaForCausalLM
LicenceApache-2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "01-ai/Yi-1.5-34B-Chat"
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.

  • yi-1.5-34b-chat stands at 29.5 (raw mean 17.1) — measured on 5 of 27 axes.

    standingtemplateVerify →

  • yi-1.5-34b-chat stands at 29.5 versus a cohort median of 34.5 across 118 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 →