Llama 3.1 Tulu3 405B

Llama 3.1 Tulu3 405B

Allen Institute for AI · Released Jan 30, 2025
Intelligence #583 / 650
11.0 our score
AA Index #276 / 398
8.3 Artificial Analysis
Input Price
Not priced
Output Price
Not priced
Context
Not reported

Analysis Summary

Tulu3 405B from the Allen Institute for AI is an open research model built on Llama 3.1, intended for instruction-following and fine-tuning experiments rather than frontier performance. Its reasoning and coding scores sit well below current generation models, and it lacks agentic or tool-use benchmarks entirely.

For businesses, this makes it more suited to internal research, fine-tuning pipelines, or low-stakes automation than client-facing deployment. Its large parameter count also means it is costly to self-host without matching capability gains.

Teams already invested in open-weight infrastructure might use it for experimentation, but most production workloads would be better served by newer, more capable open or hosted alternatives.

Assessed July 29, 2026

Editorial notes

Llama 3.1 Tulu3 405B offers open-weight flexibility but trails far behind current reasoning and coding benchmarks, limiting its use to lightweight experimentation.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

DFO Verdict

Llama 3.1 Tulu3 405B offers open-weight flexibility but trails far behind current reasoning and coding benchmarks, limiting its use to lightweight experimentation.

#583 of 650 overall Down 30 this week

Benchmark scores

GPQA Diamond 51.6%
HLE 3.5%
MMLU Pro 71.6%
MATH 500 77.8%
AIME 13.3%
SciCode 30.2%
LiveCodeBench 29.1%

Magenta = intelligence · Ink = technical/agentic · Cyan = content & long-context · Grey = community benchmarks. Data: Artificial Analysis, Hugging Face.

8.3 Intelligence Index

How Llama 3.1 Tulu3 405B compares

Llama 3.1 Tulu3 405B ranks #276 of 398 AI models we track for overall intelligence. Llama 3.1 Tulu3 405B is currently free to use via OpenRouter.

Position in the field
Intelligence: smarter than 10% of models #583
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Llama 3.1 Tulu3 405B $0.00 in $0.00 out
Anthropic: Claude Fable 5 $10.00 in $50.00 out
Claude Opus 5 $5.00 in $25.00 out
Anthropic: Claude Opus 4.8 $5.00 in $25.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Intelligence2.1Technical0Value0Content3
Performance profile

Strongest on content. The pulled-in value corner is the trade-off, and if the shape matters more than the price, this is your model.

Compare shapes side-by-side →

Frequently asked questions about Llama 3.1 Tulu3 405B

How much does Llama 3.1 Tulu3 405B cost?

Llama 3.1 Tulu3 405B is currently available for free via OpenRouter.

Who created Llama 3.1 Tulu3 405B?

Llama 3.1 Tulu3 405B is developed by Allen Institute For AI and was released on January 30, 2025.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.