Model comparison

Falcon-40B vs Wizardlm 70b

Wizardlm 70b has enough public results to be ranked (#245); Falcon-40B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Side by side

Falcon-40B and Wizardlm 70b specifications
Falcon-40BWizardlm 70b
ProviderTechnology Innovation InstituteMicrosoft
Noometry Index—32.4
Released2023-03-15—
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked1212

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

Category by category

Coding Not comparable

Falcon-40B: —, Wizardlm 70b: 30.9 (#280)

Coding benchmarks
BenchmarkFalcon-40BWizardlm 70b
LMArena Coding—1081

Reasoning Not comparable

Falcon-40B: —, Wizardlm 70b: 19.8 (#231)

Reasoning benchmarks
BenchmarkFalcon-40BWizardlm 70b
LMArena Hard Prompts—1079
BIG-Bench Hard37.1%—
Epoch Capabilities Index104.04—
HellaSwag85.3%—
LAMBADA77.3%—
PIQA83%—
WinoGrande76.9%—

Math Not comparable

Falcon-40B: —, Wizardlm 70b: 29.7 (#216)

Math benchmarks
BenchmarkFalcon-40BWizardlm 70b
LMArena Math—1116
GSM8K33.8%—

Knowledge Not comparable

Falcon-40B: —, Wizardlm 70b: —

Knowledge benchmarks
BenchmarkFalcon-40BWizardlm 70b
ARC (AI2) Challenge61.9%—
BoolQ83.1%—
MMLU56.9%—
OpenBookQA56.6%—
TriviaQA79.9%—

Multilingual Not comparable

Falcon-40B: —, Wizardlm 70b: 29.8 (#260)

Multilingual benchmarks
BenchmarkFalcon-40BWizardlm 70b
LMArena Non-English—1078
LMArena Chinese—1052
LMArena German—1083
LMArena Russian—1155

Instruction Following Not comparable

Falcon-40B: —, Wizardlm 70b: 56.5 (#268)

Instruction Following benchmarks
BenchmarkFalcon-40BWizardlm 70b
LMArena Instruction Following—1093

Long Context Not comparable

Falcon-40B: —, Wizardlm 70b: 33.3 (#258)

Long Context benchmarks
BenchmarkFalcon-40BWizardlm 70b
LMArena Longer Query—1097

Writing & Preference Not comparable

Falcon-40B: —, Wizardlm 70b: 34.9 (#264)

Writing & Preference benchmarks
BenchmarkFalcon-40BWizardlm 70b
LMArena Text—1120
LMArena Creative Writing—1149
LMArena Multi-Turn—1108

Frequently asked questions

Is Falcon-40B better than Wizardlm 70b?

Wizardlm 70b has enough public results to be ranked (#245); Falcon-40B does not yet, so treat this comparison as directional.

How many benchmarks do Falcon-40B and Wizardlm 70b share?

0 benchmarks have published results for both models. Falcon-40B has 12 scored results on Noometry and Wizardlm 70b has 12.

Related comparisons

Go deeper