priorsBuilder

Meta · released 2024-12-06

Llama 3.3 70b

Measured on 29 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. #567none of 5873.6%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #404none of 526-54.2

Leader: Opus 5.5 · 46.4

reasoning

SimpleBench

97 results
  1. #92none of 9719.9%

Leader: Opus 5.5 · 88.4%

All 29 benchmarks

show 26 more

agentic

ITBench-AA

45 results
  1. #45none of 450.6%

Leader: GPT-5.6 Sol · 56.2%

agentic

τ²-Bench Telecom

393 results
  1. #277none of 39326.6%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #190none of 28228.8%

Leader: Gemini 3 Pro · 91.7%

coding

Terminal-Bench Hard-AA

387 results
  1. #299none of 3873.0%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #209none of 2384.9%

Leader: Fable 5.1 · 91.4%

coding

WeirdML v2

127 results
  1. #121none of 12714.4%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #444none of 6107.7

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #174none of 2201318

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #172none of 2201317

Leader: Gemini 4 · 1553

economics

GDPval-AA v2.1

288 results
  1. #273none of 288-174

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #190none of 39947.1%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #310none of 52618.9%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #406none of 5269.8%

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

knowledge

Global-MMLU-Lite

118 results
  1. #86none of 11876.4%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #416none of 53949.8%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #172none of 28571.3%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #432none of 52315.7%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #199none of 2287.7%

Leader: GPT-5.2 · 99.0%

math

MATH-500

162 results
  1. #94none of 16277.3%

Leader: GPT-5 · 99.4%

reasoning

CritPt

529 results
  1. #429none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #168none of 17110.8%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #117none of 18198.9%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #136none of 3511.7s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #182none of 35192.6

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #28none of 1770.6s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #135none of 17645.0

Leader: Muse Spark 1.1 · 204.3