Model comparison

Codellama 70b Instruct vs Falcon 2 11B

Codellama 70b Instruct has enough public results to be ranked (#236); Falcon 2 11B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Side by side

Codellama 70b Instruct and Falcon 2 11B specifications
Codellama 70b InstructFalcon 2 11B
ProviderMetaTechnology Innovation Institute
Noometry Index33.3—
Released—2024-05-09
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked75

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

Category by category

Coding Not comparable

Codellama 70b Instruct: 37.0 (#189), Falcon 2 11B: —

Coding benchmarks
BenchmarkCodellama 70b InstructFalcon 2 11B
BigCodeBench Instruct40.7%—
BigCodeBench Complete49.6%—
HumanEval+65.9%—

Reasoning Not comparable

Codellama 70b Instruct: 19.2 (#241), Falcon 2 11B: —

Reasoning benchmarks
BenchmarkCodellama 70b InstructFalcon 2 11B
LMArena Hard Prompts1052—
Epoch Capabilities Index—109.25
HellaSwag—82.9%
WinoGrande—78.3%

Math Not comparable

Codellama 70b Instruct: —, Falcon 2 11B: —

Math benchmarks
BenchmarkCodellama 70b InstructFalcon 2 11B
GSM8K—53.8%

Knowledge Not comparable

Codellama 70b Instruct: —, Falcon 2 11B: —

Knowledge benchmarks
BenchmarkCodellama 70b InstructFalcon 2 11B
MMLU—58.4%

Multilingual Not comparable

Codellama 70b Instruct: 24.9 (#283), Falcon 2 11B: —

Multilingual benchmarks
BenchmarkCodellama 70b InstructFalcon 2 11B
LMArena Non-English992—

Instruction Following Not comparable

Codellama 70b Instruct: 52.1 (#288), Falcon 2 11B: —

Instruction Following benchmarks
BenchmarkCodellama 70b InstructFalcon 2 11B
LMArena Instruction Following1024—

Writing & Preference Not comparable

Codellama 70b Instruct: 33.6 (#272), Falcon 2 11B: —

Writing & Preference benchmarks
BenchmarkCodellama 70b InstructFalcon 2 11B
LMArena Text1057—

Frequently asked questions

Is Codellama 70b Instruct better than Falcon 2 11B?

Codellama 70b Instruct has enough public results to be ranked (#236); Falcon 2 11B does not yet, so treat this comparison as directional.

How many benchmarks do Codellama 70b Instruct and Falcon 2 11B share?

0 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Falcon 2 11B has 5.

Related comparisons

Go deeper