priorsBuilder

Meta · released 2025-08-27

Llama 3.1 70b

Measured on 24 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. #332default of 5878.8%
  2. #487none of 5874.5%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #330none of 526-43.1
  2. #369default of 526-49.4

Leader: Opus 5.5 · 46.4

All 24 benchmarks

show 22 more

agentic

τ²-Bench Telecom

393 results
  1. #303default of 39322.5%
  2. #310none of 39321.6%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #85default of 28265.3%
  2. #201none of 28226.9%

Leader: Gemini 3 Pro · 91.7%

coding

Terminal-Bench Hard-AA

387 results
  1. #271default of 3874.5%
  2. #301none of 3873.0%

Leader: GPT-5.6 Sol · 65.9%

coding

WeirdML v2

127 results
  1. #125none of 1279.0%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #432default of 6107.9
  2. #494none of 6106.7

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #188none of 2201293

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #186none of 2201289

Leader: Gemini 4 · 1553

instruction

IFBench

399 results
  1. #303none of 39934.4%
  2. #336default of 39931.3%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #248default of 52623.5%
  2. #300none of 52619.7%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #265none of 52621.8%
  2. #503default of 5264.6%

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

knowledge

GPQA Diamond

539 results
  1. #291default of 53969.9%
  2. #419none of 53949.1%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #78default of 28581.1%
  2. #193none of 28567.6%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #447default of 5239.7%
  2. #466none of 5234.7%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #89default of 22868.7%
  2. #192none of 22811.3%

Leader: GPT-5.2 · 99.0%

math

MATH-500

162 results
  1. #124none of 16264.9%

Leader: GPT-5 · 99.4%

reasoning

CritPt

529 results
  1. #422default of 5290.0%
  2. #461none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #161none of 1718.5%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #125none of 18198.7%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #171none of 3512.3s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #324none of 35140.5

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #9none of 1770.4s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #113none of 17651.5

Leader: Muse Spark 1.1 · 204.3