Model comparison

Falcon-180B vs Phi-3.5-mini

Falcon-180B has enough public results to be ranked (#260); Phi-3.5-mini does not yet, so treat this comparison as directional.

Last verified . 3 shared benchmarks.

Phi-3.5-mini Microsoft

36.9

Unranked Sparse

Summary

  • They share 3 benchmarks with published results for both.

Side by side

Falcon-180B and Phi-3.5-mini specifications
Falcon-180BPhi-3.5-mini
ProviderTechnology Innovation InstituteMicrosoft
Noometry Index32.236.9
Released2023-09-062024-08-16
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked165

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Falcon-180B: —, Phi-3.5-mini: 34.6 (#232)

Coding benchmarks
BenchmarkFalcon-180BPhi-3.5-mini
BigCodeBench Instruct—32.8%
BigCodeBench Complete—38.5%

Reasoning Not comparable

Falcon-180B: 19.1 (#269), Phi-3.5-mini: —

Reasoning benchmarks
BenchmarkFalcon-180BPhi-3.5-mini
PIQA84.9%81%
LMArena Hard Prompts1007—
Epoch Capabilities Index112.13—
HellaSwag89%—
LAMBADA79.8%—
WinoGrande87.1%—

Math Not comparable

Falcon-180B: —, Phi-3.5-mini: —

Math benchmarks
BenchmarkFalcon-180BPhi-3.5-mini
GSM8K54.4%86.2%

Knowledge Not comparable

Falcon-180B: —, Phi-3.5-mini: —

Knowledge benchmarks
BenchmarkFalcon-180BPhi-3.5-mini
BoolQ89%78%
ARC (AI2) Challenge67.8%—
MMLU70.6%—
OpenBookQA64.2%—

Multilingual Not comparable

Falcon-180B: 25.2 (#286), Phi-3.5-mini: —

Multilingual benchmarks
BenchmarkFalcon-180BPhi-3.5-mini
LMArena Non-English1000—

Instruction Following Not comparable

Falcon-180B: 53.4 (#286), Phi-3.5-mini: —

Instruction Following benchmarks
BenchmarkFalcon-180BPhi-3.5-mini
LMArena Instruction Following1047—

Writing & Preference Not comparable

Falcon-180B: 29.1 (#295), Phi-3.5-mini: —

Writing & Preference benchmarks
BenchmarkFalcon-180BPhi-3.5-mini
LMArena Text1054—
LMArena Creative Writing1089—
LMArena Multi-Turn1013—

Frequently asked questions

Is Falcon-180B better than Phi-3.5-mini?

Falcon-180B has enough public results to be ranked (#260); Phi-3.5-mini does not yet, so treat this comparison as directional.

How many benchmarks do Falcon-180B and Phi-3.5-mini share?

3 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Phi-3.5-mini has 5.

Related comparisons

Go deeper