Skip to content
aiqbench

Model passport

Starling Lm 7b Beta

starling-lm-7b-beta
  • Open weights
  • Apache-2.0 licence
  • Released 2024-03-19(curated)
4/27axes covered
Overall · LMArena
1,171#346 of 396
Best percentile
15.9Hard prompts
Cohort standing
29.6median 32.1

What the data says

Benchmarked on 4 of 27 tracked axes. Every figure below is the model's own published result on that board.

Weakest axes

  • 12.9 pct — Instruction following (1,146)
  • 12.9 pct — Overall (1,171)

Uneven: 3 percentile points between its best and worst axis — 15.9 pct on Hard prompts versus 12.9 pct on Instruction following.

  • Hard prompts15.9 pct1,195Verify →
  • Coding15.3 pct1,236Verify →
  • Overall12.9 pct1,171Verify →
  • Instruction following12.9 pct1,146Verify →
  • 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
  • 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.

  • starling-lm-7b-beta stands at 29.6 (raw mean 14.3) — measured on 4 of 27 axes.

    standingtemplateVerify →

  • starling-lm-7b-beta stands at 29.6 versus a cohort median of 32.1 across 106 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 →