Skip to content
aiqbench

Openchat · model passport

Openchat 3.5

openchat-3-5
  • Open weights
  • Apache-2.0 licence
  • Released 2023-11-01(curated)
6/27axes covered
Overall · LMArena
1,183#337 of 396
Best percentile
15.2Overall
Cohort standing
24.7median 27.9

What the data says

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

Weakest axes

  • 4.9 pct — MMLU-Pro (Artificial Analysis) (31.0%)
  • 12.2 pct — LiveCodeBench (Artificial Analysis) (11.5%)
  • 12.3 pct — Coding (1,203)

Uneven: 10.3 percentile points between its best and worst axis — 15.2 pct on Overall versus 4.9 pct on MMLU-Pro (Artificial Analysis).

  • Overall15.2 pct1,183Verify →
  • Instruction following14.4 pct1,155Verify →
  • Hard prompts13.4 pct1,176Verify →
  • Coding12.3 pct1,203Verify →
  • LiveCodeBench (Artificial Analysis)12.2 pct11.5%Verify →
  • MMLU-Pro (Artificial Analysis)4.9 pct31.0%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
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not 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

Repositoryopenchat/openchat_3.5
ArchitectureMistralForCausalLM
LicenceApache-2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "openchat/openchat_3.5"
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.

  • openchat-3.5 stands at 24.7 (raw mean 12) — measured on 6 of 27 axes.

    standingtemplateVerify →

  • openchat-3.5 stands at 24.7 versus a cohort median of 27.9 across 75 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 →