EBEasy BenchmarksLLM model index
Workspace
Overview
Benchmarks
Benchmarks list
Overall Index
Coding
Math
MMLU-Pro
Speed
Value
Models
All models
GPT-5.5 (xhigh)
GPT-5.5 (high)
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
Gemini 3.1 Pro Preview
GPT-5.4 (xhigh)
Artificial Analysis data
Back

Meta

Llama 3.2 Instruct 90B (Vision)

Llama 3.2 Instruct 90B (Vision) is a Meta Llama 3 family model, part of Meta's widely deployed open-weight LLM series for assistants, retrieval, coding, and self-hosted applications. The profile helps compare this specific size and instruction variant with newer open and proprietary models in the local snapshot.

Introducing Meta Llama 3

Operational Metrics

Output Speed45.8 tok/s
First Token0.54s
Blended Price$1.38/M

Model Metadata

Queryable facts extracted from the upstream model payload.

ReleaseSep 25, 2024
Context Windown/a
Modalitiesn/a
API fields: release_date

Strength: TTFT

Rank #58 across 293 models.

0.54s

Watch Area: Speed

Rank #237 across 293 models.

45.8 tok/s

Watch Area: AIME

Rank #154 across 194 models.

5.0%

Watch Area: Value

Rank #255 across 323 models.

8.6

Strength Profile

Percentile score by analysis domain.

* Cost is inverted: lower input, output, and blended prices rank higher.

Benchmark Percentiles

Higher bars mean stronger relative placement.

All Benchmarks

MetricDomainValueRank
Artificial Analysis Intelligence Indexoverall11.9#391
MMLU-Proreasoning67.1%#243
GPQAreasoning43.2%#372
Humanity's Last Examreasoning4.9%#311
LiveCodeBench
coding
21.4%
#265
SciCodecoding, reasoning24.0%#327
MATH-500math62.9%#158
AIMEmath5.0%#154
Output Speedspeed45.8 tok/s#237
Time to First Tokenspeed0.54s#58
Blended Pricecost$1.38/M#203
Input Pricecost$1.38/M#247
Output Pricecost$1.38/M#132
Value Indexcost, overall8.6#255