The Model Index
Models/DeepSeek

DeepSeek LLM 67B

DeepSeekOpen weights

DeepSeek LLM 67B is an open-weights AI model from DeepSeek with an index score of 87 (GPT-4 = 100), provisional.

8763–112Index scoreProvisional · one third-party tester so far; ranked once a second confirms it
–Price per million tokensno public API price found
–Context windowtokens it reads at once
29 Nov 2023Released3 years ago

Where it sitson the frontier

801001201401601802002023202420252026GPT-4 at launch = 100DeepSeek LLM 67B

GPT-4 reached this score 9 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence
GPQA Diamond (Epoch AI)
25%
Humanity's Last Exam
no result
Mathsevidence
FrontierMath (tiers 1-3)
no result
Codingno evidence yet
SWE-bench Verified
no result
Terminal-Bench 4.0
no result
Agentsno evidence yet
APEX-Agents
no result
Professional workno evidence yet
Finance Agent (v2)
no result
Novel problemsno evidence yet
ARC-AGI-2
no result
Long tasksno evidence yet
METR time horizon
no result

Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.

What others sayrank on 6 leaderboards

Best attop three among current models

Not in the top three among current models on any category we track.

Facts and sources

Released29 Nov 2023
Announcementnot linked yet
Release entryDeepSeek LLM 67B
Scored asDeepSeek LLM 67B
Output speed–
Hugging Facenot linked

DeepSeek releasesaround this one

This page as a chartDownload PNG