DeepSeek
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well...
Running this yourself: can likely run on your own machine.
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.
65.8
Quality Score
1382
Arena ELO
685B
Parameters
164K
Context
Use this section to answer one simple question first: how much outside evidence do we have that this model performs well? Structured benchmark scores appear first, then official provider evidence, then live arena signal.
This model has normalized benchmark rows, so scores here are directly comparable across benchmark sources.
Sign in to join the discussion
0
Downloads
0
Likes
Mar 2025
Released
These are recent benchmark or leaderboard claims from official provider sources. They are useful for freshness and context, but they are not treated the same as normalized independent benchmark rows.
deepseek-v3-0324 — LiveBench Scores
language: 0.7 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.7
View sourceDeepSeek V3 0324 Benchmark Update
Quality: 22.3/100 | Price: $1.209/M tokens | Output: 0 tok/s | MMLU: 0.819% | HumanEval: 0.405%
View sourceDeepSeek-V3-0324 - SWE-Bench Verified
SWE-Bench Verified resolved rate 42.0
View sourceDeepSeek V3 0324 Benchmark Update
Quality: 22.3/100 | Price: $1.209/M tokens | Output: 0 tok/s | MMLU: 0.819% | HumanEval: 0.405%
View sourcedeepseek-v3-0324 — LiveBench Scores
language: 0.7 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.7
View sourceDeepSeek V3 0324 Benchmark Update
Quality: 22.3/100 | Price: $1.209/M tokens | Output: 0 tok/s | MMLU: 0.819% | HumanEval: 0.405%
View source1382
ELO Score
1378 - 1387
95% Confidence
+/-5 points
23.0K
Battles
May 30, 2026
Last Updated