priorsBuilder

Meta · released 2025-08-27

Llama 3.1 405b

Measured on 21 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. #298default of 58710.9%
  2. #506none of 5874.2%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #223none of 526-17.1
  2. #294default of 526-36.0

Leader: Opus 5.5 · 46.4

reasoning

SimpleBench

97 results
  1. #86none of 9723.0%

Leader: Opus 5.5 · 88.4%

All 21 benchmarks

show 18 more

agentic

τ²-Bench Telecom

393 results
  1. #278none of 39326.6%
  2. #306default of 39322.2%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #72default of 28268.6%
  2. #115none of 28254.6%

Leader: Gemini 3 Pro · 91.7%

coding

Terminal-Bench Hard-AA

387 results
  1. #215default of 38711.4%
  2. #226none of 3879.8%

Leader: GPT-5.6 Sol · 65.9%

coding

WeirdML v2

127 results
  1. #117none of 12721.4%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #453default of 6107.5
  2. #459none of 6107.4

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #166none of 2201335

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #158none of 2201340

Leader: Gemini 4 · 1553

instruction

IFBench

399 results
  1. #265none of 39939.0%
  2. #323default of 39932.7%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #177default of 52630.1%
  2. #212none of 52626.1%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #127none of 52647.6%
  2. #490default of 5265.5%

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

knowledge

GPQA Diamond

539 results
  1. #270default of 53972.7%
  2. #399none of 53953.6%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #52default of 28582.9%
  2. #161none of 28573.2%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #393none of 52325.3%
  2. #403default of 52322.3%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #86default of 22869.7%
  2. #181none of 22815.3%

Leader: GPT-5.2 · 99.0%

math

MATH-500

162 results
  1. #115none of 16270.3%

Leader: GPT-5 · 99.4%

reasoning

CritPt

529 results
  1. #303default of 5290.3%
  2. #440none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

speed

Latency (Time to First Token)

351 results
  1. #174default of 3512.3s
  2. #175none of 3512.4s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #322default of 35140.9
  2. #330none of 35137.6

Leader: Celeris-1 · 1522.5