modelgrep
P

Prime Intellect: INTELLECT-3

prime-intellect/intellect-3

112th smartest of 178ReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
22.2
112th of 178
Design Elo
1167
3D
Speed
58
142nd fastest
Latency
183ms
first token
Input price
$0.200
97th cheapest
Context
131K
131K max out

How it compares

Smarter than37%
of all ranked models
Faster than52%
of all ranked models
Cheaper than67%
of all ranked models

Overview

INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offers state-of-the-art performance for its size across math,...

Benchmarks

independent · via OpenRouter
Artificial Analysis37th percentile
Intelligence Index
22.2
Coding Index
19.1
Agentic Index
19.8
GPQA Diamond
76%
Humanity's Last Exam
12%
SciCode
39%
Tau²-Bench (agentic)
27%
Design Arena · Elo15,070 tournaments
3D
1167
Website
1161
codecategories
1158
Game Dev
1146
UI Component
1134
Data Viz
1126
svg
1048
asciiart
1003

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Nebiusfp8$0.200$1.10

Specifications

Context window131K
Max output131K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

INTELLECT-3 FAQ

How much does INTELLECT-3 cost?

INTELLECT-3 costs $0.200 per million input tokens and $1.10 per million output tokens via OpenRouter, making it 97th cheapest of 298 paid models.

How smart is INTELLECT-3?

INTELLECT-3 scores 22.2 on the Artificial Analysis Intelligence Index, ranking 112th of 178 benchmarked models, with a GPQA Diamond score of 76%.

How fast is INTELLECT-3?

INTELLECT-3 generates around 58 tokens per second with 183ms time-to-first-token (p50), the 142nd fastest tracked model.

What is INTELLECT-3's context window?

INTELLECT-3 supports a 131K-token context window and can output up to 131K tokens. It accepts text input.

Compare head-to-head