Neura Intelligence Index

AI Model Benchmarks

Jamba 1.5 Large vs Phi-3.5-MoE-instruct — Benchmark Comparison | Neura Market

Back to Leaderboard

Jamba 1.5 Large vs Phi-3.5-MoE-instruct

Jamba 1.5 Large

AI21 Labs 🇮🇱

5.8

#354—

Phi-3.5-MoE-instruct

Microsoft 🇺🇸

6.8

#351—

Category Comparison

Benchmark-by-Benchmark

reasoning

Benchmark	Jamba 1.5 Large	Phi-3.5-MoE-instruct
GPQA Diamond	36.9	36.8

general

Benchmark	Jamba 1.5 Large	Phi-3.5-MoE-instruct
MMMLU	—	69.9

Category Winners

reasoning

Jamba 1.5 Large

5.8

general

Phi-3.5-MoE-instruct

8.0