Llama 3.1 Tulu3 405B

Llama 3.1 Tulu3 405B

Allen Institute for AI · Released Jan 30, 2025
Intelligence #9 / 612
82.0 our score
AA Index #270 / 393
8.3 Artificial Analysis
Input Price
– Not priced
Output Price
– Not priced
Context
– Not reported

Analysis Summary

Llama 3.1 Tulu3 405B is Allen Institute for AI's large open-weight instruction-tuned model, built on the Llama 3.1 base. It shows reasonable general knowledge performance but weak scores on reasoning-heavy and coding benchmarks compared to current models.

For businesses, this suits self-hosted deployments where data control matters more than raw capability, such as internal knowledge tools or lightly supervised drafting tasks. It is not well suited to complex coding or agentic workflows given its limited coding and reasoning results.

As an open model, cost is largely determined by hosting infrastructure. Consider it only where self-hosting is a priority and task complexity is modest.

Assessed July 10, 2026

Editorial notes

Tulu3 405B from Allen Institute offers open-weight flexibility and solid knowledge recall, but reasoning and coding results trail current frontier models by a wide margin.

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

DFO Verdict

Tulu3 405B from Allen Institute offers open-weight flexibility and solid knowledge recall, but reasoning and coding results trail current frontier models by a wide margin.

#9 of 612 overall

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 Ā· Ink = technical/agentic Ā· Cyan = content & long-context Ā· 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 #270 of 393 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 99% of models #9
worst in fieldmedianbest in field
Price vs frontier peers Ā· $ per 1M tokens
Llama 3.1 Tulu3 405B $0.00 in $0.00 out
Anthropic: Claude Fable 5 $10.00 in $50.00 out
Anthropic: Claude Opus 4.8 $5.00 in $25.00 out
Google: Gemini 3.1 Pro Preview $2.00 in $12.00 out

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

Context window vs peers Ā· tokens

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

Intelligence2.1Technical0Value0Content0
Performance profile

Strongest on intelligence. 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 →

Embed this ranking

Writing about this model? Add the badge to your site. It always shows the current rank and score, and links back to this page.

Llama 3.1 Tulu3 405B rank badge, Dark
<a href="https://designforonline.com/ai-models/ai2-llama-3-1-tulu3-405b/"><img src="https://designforonline.com/?aiml_badge=ai2-llama-3-1-tulu3-405b&theme=dark" alt="Llama 3.1 Tulu3 405B, ranked #9 on the Design for Online AI Leaderboard" width="400" height="76"></a>
Llama 3.1 Tulu3 405B rank badge, Light
<a href="https://designforonline.com/ai-models/ai2-llama-3-1-tulu3-405b/"><img src="https://designforonline.com/?aiml_badge=ai2-llama-3-1-tulu3-405b&theme=light" alt="Llama 3.1 Tulu3 405B, ranked #9 on the Design for Online AI Leaderboard" width="400" height="76"></a>

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.