Model comparison

Falcon-40B vs Phi 3 Mini 128k Instruct

Phi 3 Mini 128k Instruct has enough public results to be ranked (#305); Falcon-40B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Side by side

Falcon-40B and Phi 3 Mini 128k Instruct specifications
Falcon-40BPhi 3 Mini 128k Instruct
ProviderTechnology Innovation InstituteMicrosoft
Noometry Index—29.7
Released2023-03-152024-04-23
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked1219

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

Category by category

Coding Not comparable

Falcon-40B: —, Phi 3 Mini 128k Instruct: 28.8 (#312)

Coding benchmarks
BenchmarkFalcon-40BPhi 3 Mini 128k Instruct
BigCodeBench Instruct—29.6%
LMArena Coding—1039
BigCodeBench Complete—40.6%

Reasoning Not comparable

Falcon-40B: —, Phi 3 Mini 128k Instruct: 19.6 (#256)

Reasoning benchmarks
BenchmarkFalcon-40BPhi 3 Mini 128k Instruct
LMArena Hard Prompts—1028
BIG-Bench Hard37.1%—
Epoch Capabilities Index104.45—
HellaSwag85.3%—
LAMBADA77.3%—
PIQA83%—
WinoGrande76.9%—

Math Not comparable

Falcon-40B: —, Phi 3 Mini 128k Instruct: 31.6 (#222)

Math benchmarks
BenchmarkFalcon-40BPhi 3 Mini 128k Instruct
LMArena Math—1089
GSM8K33.8%—

Knowledge Not comparable

Falcon-40B: —, Phi 3 Mini 128k Instruct: 26.8 (#254)

Knowledge benchmarks
BenchmarkFalcon-40BPhi 3 Mini 128k Instruct
LMArena Expert—984
ARC (AI2) Challenge61.9%—
BoolQ83.1%—
MMLU56.9%—
OpenBookQA56.6%—
TriviaQA79.9%—

Multilingual Not comparable

Falcon-40B: —, Phi 3 Mini 128k Instruct: 25.2 (#285)

Multilingual benchmarks
BenchmarkFalcon-40BPhi 3 Mini 128k Instruct
LMArena Non-English—1000
LMArena Chinese—1016
LMArena French—1039
LMArena German—1006
LMArena Japanese—899
LMArena Korean—856
LMArena Russian—1004
LMArena Spanish—1059

Instruction Following Not comparable

Falcon-40B: —, Phi 3 Mini 128k Instruct: 51.8 (#294)

Instruction Following benchmarks
BenchmarkFalcon-40BPhi 3 Mini 128k Instruct
LMArena Instruction Following—1023

Long Context Not comparable

Falcon-40B: —, Phi 3 Mini 128k Instruct: 30.4 (#289)

Long Context benchmarks
BenchmarkFalcon-40BPhi 3 Mini 128k Instruct
LMArena Longer Query—996

Writing & Preference Not comparable

Falcon-40B: —, Phi 3 Mini 128k Instruct: 27.1 (#301)

Writing & Preference benchmarks
BenchmarkFalcon-40BPhi 3 Mini 128k Instruct
LMArena Text—1050
LMArena Creative Writing—1024
LMArena Multi-Turn—989

Frequently asked questions

Is Falcon-40B better than Phi 3 Mini 128k Instruct?

Phi 3 Mini 128k Instruct has enough public results to be ranked (#305); Falcon-40B does not yet, so treat this comparison as directional.

How many benchmarks do Falcon-40B and Phi 3 Mini 128k Instruct share?

0 benchmarks have published results for both models. Falcon-40B has 12 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.

Related comparisons

Go deeper