priorsBuilder

Meta · released 2024-04-18

Llama 3 8b

Measured on 16 benchmarks.

General frontier

Not ranked in this mix — too little measured data for its benchmarks.

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #436none of 5875.1%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #487none of 526-70.1

Leader: Opus 5.5 · 46.4

All 16 benchmarks

show 14 more

agentic

τ²-Bench Telecom

393 results
  1. #392none of 3930.0%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #261none of 2829.6%

Leader: Gemini 3 Pro · 91.7%

coding

Terminal-Bench Hard-AA

387 results
  1. #384none of 3870.0%

Leader: GPT-5.6 Sol · 65.9%

composite

AA Intelligence Index v4.3.2

610 results
  1. #602none of 6104.8

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #204none of 2201224

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #203none of 2201206

Leader: Gemini 4 · 1553

instruction

IFBench

399 results
  1. #373none of 39924.6%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #463none of 52610.4%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #398none of 52610.2%

Leader: MiniCPM5-1B (Non-reasoning) · 99.1%

knowledge

GPQA Diamond

539 results
  1. #505none of 53929.6%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #262none of 28540.5%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #518none of 5230.0%

Leader: Kimi K3 · 88.7%

math

MATH-500

162 results
  1. #137none of 16249.9%

Leader: GPT-5 · 99.4%

reasoning

CritPt

529 results
  1. #519none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%