Skip to content
aiqbench

Ant-Group · model passport

Ring Flash 2.0

ring-flash-2-0
  • Open weights
  • MIT licence
  • 102.9B params
  • Released 2025-09-19(HF repo created)
7/27axes covered
Overall · LMArena
1,323#236 of 396
Best percentile
66.0LiveCodeBench (Artificial Analysis)
Cohort standing
50.8median 52.6

What the data says

Benchmarked on 7 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 25.3 percentile points between its best and worst axis — 66 pct on LiveCodeBench (Artificial Analysis) versus 40.7 pct on Overall.

  • LiveCodeBench (Artificial Analysis)66 pct62.8%Verify →
  • MMLU-Pro (Artificial Analysis)64 pct79.3%Verify →
  • Coding48.3 pct1,390Verify →
  • IFBench (Artificial Analysis)48.1 pct43.3%Verify →
  • Hard prompts46 pct1,352Verify →
  • Instruction following44.7 pct1,316Verify →
  • Overall40.7 pct1,323Verify →
  • 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
  • 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

RepositoryinclusionAI/Ring-flash-2.0
Parameters102.9B
ArchitectureBailingMoeV2ForCausalLM
LicenceMIT

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "inclusionAI/Ring-flash-2.0"
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.

  • ring-flash-2.0 stands at 50.8 (raw mean 51.1) — measured on 7 of 27 axes.

    standingtemplateVerify →

  • ring-flash-2.0 stands at 50.8 versus a cohort median of 52.6 across 147 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 →