Llama-3.1-8B-MultiReflection-Instruct

leafspark

Parameters

Downloads

—

Likes

—

Avg score

26.9

6 benchmarks

Weights

Open

Released

—

About

Llama-3.1-8B-MultiReflection-Instruct is a 8B-parameter open-weights model in the Llama family from leafspark. Benchmarked on 6 evals, averaging 26.9.

llama3.1

Benchmark scores · 6

avg 26.9 — higher is better

IFEvalOpen LLM LB · 2026-05

71.3

MMLU-ProOpen LLM LB · 2026-05

30.3

BIG-Bench HardOpen LLM LB · 2026-05

28.4

MATH Lvl 5Open LLM LB · 2026-05

17.1

MuSROpen LLM LB · 2026-05

8.5

GPQA DiamondOpen LLM LB · 2026-05

5.7

Details

Publisherleafspark

FamilyLlama

Parameters8B

Licensellama3.1

WeightsOpen

Released—

History

full ledger →

Capability over time

Append-only ledger — every observed change to this model's numbers.