Model comparison
Falcon-180B vs Llama 2-13B
Falcon-180B is the stronger model overall, scoring 32.2 to 29.6 on the Noometry Index.
Last verified . 16 shared benchmarks.
Technology Innovation Institute
MetaSummary
- They share 16 benchmarks with published results for both. Falcon-180B scores higher in 2 categories and Llama 2-13B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Falcon-180B leads 19.1 to 12.8.
Side by side
| Falcon-180B | Llama 2-13B | |
|---|---|---|
| Provider | Technology Innovation Institute | Meta |
| Noometry Index | 32.2 | 29.6 |
| Released | 2023-09-06 | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Llama 2-13B: 30.9 (#291)
| Benchmark | Falcon-180B | Llama 2-13B |
|---|---|---|
| LMArena Coding | — | 1062 |
Reasoning Falcon-180B leads
Falcon-180B: 19.1 (#269), Llama 2-13B: 12.8 (#337)
| Benchmark | Falcon-180B | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1051 |
| Epoch Capabilities Index | 112.13 | 106.17 |
| HellaSwag | 89% | 80.7% |
| LAMBADA | 79.8% | 76.5% |
| PIQA | 84.9% | 80.8% |
| WinoGrande | 87.1% | 72.8% |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
Math Not comparable
Falcon-180B: —, Llama 2-13B: 31.1 (#229)
| Benchmark | Falcon-180B | Llama 2-13B |
|---|---|---|
| GSM8K | 54.4% | 36.9% |
| LMArena Math | — | 1065 |
Knowledge Not comparable
Falcon-180B: —, Llama 2-13B: 28.1 (#249)
| Benchmark | Falcon-180B | Llama 2-13B |
|---|---|---|
| ARC (AI2) Challenge | 67.8% | 60.3% |
| BoolQ | 89% | 82.4% |
| MMLU | 70.6% | 55.6% |
| OpenBookQA | 64.2% | 57% |
| LMArena Expert | — | 1030 |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Falcon-180B: —, Llama 2-13B: —
| Benchmark | Falcon-180B | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual Llama 2-13B leads
Falcon-180B: 25.2 (#286), Llama 2-13B: 26.5 (#279)
| Benchmark | Falcon-180B | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1000 | 1024 |
| LMArena Chinese | — | 1001 |
| LMArena French | — | 1044 |
| LMArena German | — | 1009 |
| LMArena Japanese | — | 894 |
| LMArena Korean | — | 953 |
| LMArena Russian | — | 1055 |
| LMArena Spanish | — | 1087 |
Instruction Following Too close to call
Falcon-180B: 53.4 (#286), Llama 2-13B: 53.3 (#287)
| Benchmark | Falcon-180B | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1047 | 1045 |
Long Context Not comparable
Falcon-180B: —, Llama 2-13B: 32.3 (#269)
| Benchmark | Falcon-180B | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | — | 1064 |
Writing & Preference Too close to call
Falcon-180B: 29.1 (#295), Llama 2-13B: 29.8 (#289)
| Benchmark | Falcon-180B | Llama 2-13B |
|---|---|---|
| LMArena Text | 1054 | 1084 |
| LMArena Creative Writing | 1089 | 1047 |
| LMArena Multi-Turn | 1013 | 1050 |
Frequently asked questions
Is Falcon-180B better than Llama 2-13B?
Falcon-180B is the stronger model overall, scoring 32.2 to 29.6 on the Noometry Index.
How many benchmarks do Falcon-180B and Llama 2-13B share?
16 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Llama 2-13B has 32.