Phi-3.5-mini-instruct
microsoft
BenchClub cloud
- Pass rate
- 64%
- 23 of 36 checks
- Speed
- 261.3 tok/s
- decode, short prompt
- At 8k context
- 203.8 tok/s
- decode
- Cloud runs
- 6
- speeds within 2.6%
- Coding9/1850%
- Tool useNot supported by this model
- Long context14/1878%
- Suite
- [email protected]
- Machine
- NVIDIA L40S · 48 GB
- Engine
- ollama 0.40.14
Headline numbers come only from cloud runs. Runs on members’ own machines are listed below and don’t change them.
LMArena
Not ranked on LMArena
LMArena only ranks the models it serves.
BenchClub runs
Run this modelRun byWhereSpeed
Alex RiveraNov 6, 2026RTX 4060 Ti · 16 GB89.3 tok/s
Hana KimNov 5, 2026Apple M4 Pro · 24 GB74.1 tok/s
- Kwame MensahOct 29, 2026RTX 3090 · 24 GB263.8 tok/s
- Jana NovákováOct 28, 2026Apple M1 Max · 64 GB112.0 tok/s
- Priya RamanOct 27, 2026RTX 4070 Ti SUPER · 16 GB190.7 tok/s
- Mei TanakaOct 25, 2026Apple M4 Pro · 24 GB73.5 tok/s
Ivy ChenOct 24, 2026L40S · 48 GBCloud260.3 tok/s
Samir HaddadOct 17, 2026L40S · 48 GBCloud262.3 tok/s
- Fatima ZahraOct 16, 2026L40S · 48 GBCloud260.1 tok/s
PassedFailedNot supported