Meta
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
Running this yourself: can likely run on your own machine.
43.9
Quality Score
1147
Arena ELO
17B
Parameters
1M
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
Apr 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.
llama-4-maverick-instruct - SWE-Bench Verified
SWE-Bench Verified resolved rate 21.0
View sourceLlama 4 Maverick Benchmark Update
Quality: 18.4/100 | Price: $0.475/M tokens | Output: 127.179 tok/s | MMLU: 0.809% | HumanEval: 0.397%
View source1147
ELO Score
1138 - 1156
95% Confidence
+/-9 points
7.1K
Battles
May 21, 2026
Last Updated