priorsBuilder

Meta · released 2024-07-23

Llama 3.1 8b

Measured on 28 benchmarks.

General frontier

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

Your mix’s benchmarks

3 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #422none of 5875.3%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #276none of 526-30.9

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #159medium of 19614.0%

Leader: Opus 4.8 · 95.0%

All 28 benchmarks

show 25 more

agentic

τ²-Bench Telecom

393 results
  1. #336none of 39316.4%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #249none of 28211.6%

Leader: Gemini 3 Pro · 91.7%

coding

Terminal-Bench Hard-AA

387 results
  1. #329none of 3870.8%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #225none of 2381.5%

Leader: Fable 5.1 · 91.4%

coding

WeirdML v2

127 results
  1. #127medium of 1271.7%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #482none of 6106.9

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #206medium of 2201211

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #205medium of 2201198

Leader: Gemini 4 · 1553

economics

GDPval-AA v2.1

288 results
  1. #282none of 288-387

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #349none of 39928.6%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #487none of 5268.5%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #84none of 52657.0%

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

knowledge

Global-MMLU-Lite

118 results
  1. #117none of 11835.1%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #520none of 53927.0%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #246none of 28547.6%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #424none of 52318.0%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #211none of 2284.3%

Leader: GPT-5.2 · 99.0%

math

MATH-500

162 results
  1. #135none of 16251.9%

Leader: GPT-5 · 99.4%

reasoning

CritPt

529 results
  1. #454none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #142medium of 1715.1%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #101medium of 18199.3%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #45none of 3510.9s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #100none of 351141.1

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #13medium of 1770.4s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #29medium of 176102.0

Leader: Muse Spark 1.1 · 204.3