Model comparison
Falcon-180B vs Llama 13b
Falcon-180B is the stronger model overall, scoring 32.2 to 24.4 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 4 categories and Llama 13b in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Falcon-180B leads 53.4 to 36.7.
Side by side
| Falcon-180B | Llama 13b | |
|---|---|---|
| Provider | Technology Innovation Institute | Meta |
| Noometry Index | 32.2 | 24.4 |
| Released | 2023-09-06 | 2023-02-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Llama 13b: 21.4 (#337)
| Benchmark | Falcon-180B | Llama 13b |
|---|---|---|
| LMArena Coding | — | 683 |
Reasoning Falcon-180B leads
Falcon-180B: 19.1 (#269), Llama 13b: 14.0 (#329)
| Benchmark | Falcon-180B | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1007 | 728 |
| Epoch Capabilities Index | 112.13 | 100.58 |
| HellaSwag | 89% | 79.2% |
| LAMBADA | 79.8% | 75.2% |
| PIQA | 84.9% | 80.1% |
| WinoGrande | 87.1% | 73% |
| BIG-Bench Hard | — | 37.9% |
Math Not comparable
Falcon-180B: —, Llama 13b: 26.7 (#256)
| Benchmark | Falcon-180B | Llama 13b |
|---|---|---|
| GSM8K | 54.4% | 20.6% |
| LMArena Math | — | 838 |
Knowledge Not comparable
Falcon-180B: —, Llama 13b: —
| Benchmark | Falcon-180B | Llama 13b |
|---|---|---|
| ARC (AI2) Challenge | 67.8% | 52.7% |
| BoolQ | 89% | 78.7% |
| MMLU | 70.6% | 47.7% |
| OpenBookQA | 64.2% | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Falcon-180B: —, Llama 13b: —
| Benchmark | Falcon-180B | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual Falcon-180B leads
Falcon-180B: 25.2 (#286), Llama 13b: 16.6 (#297)
| Benchmark | Falcon-180B | Llama 13b |
|---|---|---|
| LMArena Non-English | 1000 | 819 |
Instruction Following Falcon-180B leads
Falcon-180B: 53.4 (#286), Llama 13b: 36.7 (#305)
| Benchmark | Falcon-180B | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1047 | 781 |
Writing & Preference Falcon-180B leads
Falcon-180B: 29.1 (#295), Llama 13b: 13.8 (#312)
| Benchmark | Falcon-180B | Llama 13b |
|---|---|---|
| LMArena Text | 1054 | 834 |
| LMArena Creative Writing | 1089 | 794 |
| LMArena Multi-Turn | 1013 | 753 |
Frequently asked questions
Is Falcon-180B better than Llama 13b?
Falcon-180B is the stronger model overall, scoring 32.2 to 24.4 on the Noometry Index.
How many benchmarks do Falcon-180B and Llama 13b share?
16 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Llama 13b has 21.