Model comparison
Codellama 34b Instruct vs Falcon-180B
Falcon-180B is the stronger model overall, scoring 32.2 to 30.8 on the Noometry Index.
Last verified . 6 shared benchmarks.
Meta
Technology Innovation InstituteSummary
- They share 6 benchmarks with published results for both. Codellama 34b Instruct scores higher in 2 categories and Falcon-180B in 2 categories; one gap is clear of the uncertainty.
Side by side
| Codellama 34b Instruct | Falcon-180B | |
|---|---|---|
| Provider | Meta | Technology Innovation Institute |
| Noometry Index | 30.8 | 32.2 |
| Released | — | 2023-09-06 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Codellama 34b Instruct: 28.5 (#314), Falcon-180B: —
| Benchmark | Codellama 34b Instruct | Falcon-180B |
|---|---|---|
| BigCodeBench Instruct | 29% | — |
| LMArena Coding | 1046 | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Too close to call
Codellama 34b Instruct: 19.6 (#255), Falcon-180B: 19.1 (#269)
| Benchmark | Codellama 34b Instruct | Falcon-180B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1007 |
| Epoch Capabilities Index | — | 112.13 |
| HellaSwag | — | 89% |
| LAMBADA | — | 79.8% |
| PIQA | — | 84.9% |
| WinoGrande | — | 87.1% |
Math Not comparable
Codellama 34b Instruct: 31.0 (#230), Falcon-180B: —
| Benchmark | Codellama 34b Instruct | Falcon-180B |
|---|---|---|
| LMArena Math | 1056 | — |
| GSM8K | — | 54.4% |
Knowledge Not comparable
Codellama 34b Instruct: —, Falcon-180B: —
| Benchmark | Codellama 34b Instruct | Falcon-180B |
|---|---|---|
| ARC (AI2) Challenge | — | 67.8% |
| BoolQ | — | 89% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 64.2% |
Multilingual Too close to call
Codellama 34b Instruct: 25.8 (#284), Falcon-180B: 25.2 (#286)
| Benchmark | Codellama 34b Instruct | Falcon-180B |
|---|---|---|
| LMArena Non-English | 1011 | 1000 |
| LMArena Chinese | 976 | — |
Instruction Following Falcon-180B leads
Codellama 34b Instruct: 52.2 (#291), Falcon-180B: 53.4 (#286)
| Benchmark | Codellama 34b Instruct | Falcon-180B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1047 |
Long Context Not comparable
Codellama 34b Instruct: 30.9 (#284), Falcon-180B: —
| Benchmark | Codellama 34b Instruct | Falcon-180B |
|---|---|---|
| LMArena Longer Query | 1013 | — |
Writing & Preference Too close to call
Codellama 34b Instruct: 28.2 (#297), Falcon-180B: 29.1 (#295)
| Benchmark | Codellama 34b Instruct | Falcon-180B |
|---|---|---|
| LMArena Text | 1066 | 1054 |
| LMArena Creative Writing | 1032 | 1089 |
| LMArena Multi-Turn | 1015 | 1013 |
Frequently asked questions
Is Codellama 34b Instruct better than Falcon-180B?
Falcon-180B is the stronger model overall, scoring 32.2 to 30.8 on the Noometry Index.
How many benchmarks do Codellama 34b Instruct and Falcon-180B share?
6 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Falcon-180B has 16.