Model passport

Dbrx Instruct Preview

dbrx-instruct-preview

Open weights
DBRX LICENSE licence
Released 2024-03-27(curated)

Overall · LMArena: 1,196#330 of 396
Best percentile: 18.2Coding
Cohort standing: 31.5median 32.6

What the data says

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

Uneven: 1.3 percentile points between its best and worst axis — 18.2 pct on Coding versus 16.9 pct on Overall.

Coding18.2 pct1,251Verify →
Instruction following17.9 pct1,188Verify →
Hard prompts17.7 pct1,218Verify →
Overall16.9 pct1,196Verify →
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.

dbrx-instruct-preview stands at 31.5 (raw mean 17.7) — measured on 4 of 27 axes.
standingtemplateVerify →
dbrx-instruct-preview stands at 31.5 versus a cohort median of 32.6 across 107 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 →