Model comparison
Codellama 70b Instruct vs Falcon-180B
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 32.2 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
Technology Innovation InstituteSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 2 categories and Falcon-180B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Codellama 70b Instruct leads 33.4 to 29.1.
Side by side
| Codellama 70b Instruct | Falcon-180B | |
|---|---|---|
| Provider | Meta | Technology Innovation Institute |
| Noometry Index | 33.7 | 32.2 |
| Released | — | 2023-09-06 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Codellama 70b Instruct: 37.6 (#193), Falcon-180B: —
| Benchmark | Codellama 70b Instruct | Falcon-180B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Too close to call
Codellama 70b Instruct: 20.1 (#242), Falcon-180B: 19.1 (#269)
| Benchmark | Codellama 70b Instruct | Falcon-180B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1007 |
| Epoch Capabilities Index | — | 112.13 |
| HellaSwag | — | 89% |
| LAMBADA | — | 79.8% |
| PIQA | — | 84.9% |
| WinoGrande | — | 87.1% |
Math Not comparable
Codellama 70b Instruct: —, Falcon-180B: —
| Benchmark | Codellama 70b Instruct | Falcon-180B |
|---|---|---|
| GSM8K | — | 54.4% |
Knowledge Not comparable
Codellama 70b Instruct: —, Falcon-180B: —
| Benchmark | Codellama 70b Instruct | Falcon-180B |
|---|---|---|
| ARC (AI2) Challenge | — | 67.8% |
| BoolQ | — | 89% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 64.2% |
Multilingual Too close to call
Codellama 70b Instruct: 24.8 (#288), Falcon-180B: 25.2 (#286)
| Benchmark | Codellama 70b Instruct | Falcon-180B |
|---|---|---|
| LMArena Non-English | 992 | 1000 |
Instruction Following Falcon-180B leads
Codellama 70b Instruct: 51.9 (#293), Falcon-180B: 53.4 (#286)
| Benchmark | Codellama 70b Instruct | Falcon-180B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1047 |
Writing & Preference Codellama 70b Instruct leads
Codellama 70b Instruct: 33.4 (#277), Falcon-180B: 29.1 (#295)
| Benchmark | Codellama 70b Instruct | Falcon-180B |
|---|---|---|
| LMArena Text | 1057 | 1054 |
| LMArena Creative Writing | — | 1089 |
| LMArena Multi-Turn | — | 1013 |
Frequently asked questions
Is Codellama 70b Instruct better than Falcon-180B?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 32.2 on the Noometry Index.
How many benchmarks do Codellama 70b Instruct and Falcon-180B share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Falcon-180B has 16.