Model comparison
Falcon-180B vs Llama 2-70B
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 1 category and Llama 2-70B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Falcon-180B leads 19.1 to 14.4.
Side by side
| Falcon-180B | Llama 2-70B | |
|---|---|---|
| Provider | Technology Innovation Institute | Meta |
| Noometry Index | 32.2 | 24.4 |
| Released | 2023-09-06 | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Llama 2-70B: 31.4 (#286)
| Benchmark | Falcon-180B | Llama 2-70B |
|---|---|---|
| LMArena Coding | — | 1079 |
Reasoning Falcon-180B leads
Falcon-180B: 19.1 (#269), Llama 2-70B: 14.4 (#325)
| Benchmark | Falcon-180B | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1073 |
| Epoch Capabilities Index | 112.13 | 113.79 |
| HellaSwag | 89% | 85.3% |
| LAMBADA | 79.8% | 78.9% |
| PIQA | 84.9% | 82.8% |
| WinoGrande | 87.1% | 80.2% |
| DTBench | — | 41.6% |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| ForecastBench | — | 51.4 |
Math Not comparable
Falcon-180B: —, Llama 2-70B: 8.1 (#326)
| Benchmark | Falcon-180B | Llama 2-70B |
|---|---|---|
| GSM8K | 54.4% | 69.6% |
| OTIS Mock AIME 2024-2025 | — | 0% |
| LMArena Math | — | 1091 |
| MATH Level 5 | — | 3.3% |
Knowledge Not comparable
Falcon-180B: —, Llama 2-70B: 7.4 (#310)
| Benchmark | Falcon-180B | Llama 2-70B |
|---|---|---|
| ARC (AI2) Challenge | 67.8% | 78.3% |
| BoolQ | 89% | 88.6% |
| MMLU | 70.6% | 69.9% |
| OpenBookQA | 64.2% | 60.2% |
| GPQA Diamond | — | 26.3% |
| LMArena Expert | — | 1039 |
| TriviaQA | — | 87.6% |
Multilingual Llama 2-70B leads
Falcon-180B: 25.2 (#286), Llama 2-70B: 27.7 (#274)
| Benchmark | Falcon-180B | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1000 | 1045 |
| LMArena Chinese | — | 995 |
| LMArena French | — | 1090 |
| LMArena German | — | 1041 |
| LMArena Japanese | — | 927 |
| LMArena Korean | — | 964 |
| LMArena Russian | — | 1083 |
| LMArena Spanish | — | 1143 |
Instruction Following Llama 2-70B leads
Falcon-180B: 53.4 (#286), Llama 2-70B: 54.9 (#278)
| Benchmark | Falcon-180B | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1047 | 1071 |
Long Context Not comparable
Falcon-180B: —, Llama 2-70B: 32.3 (#270)
| Benchmark | Falcon-180B | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | — | 1062 |
Writing & Preference Llama 2-70B leads
Falcon-180B: 29.1 (#295), Llama 2-70B: 32.3 (#279)
| Benchmark | Falcon-180B | Llama 2-70B |
|---|---|---|
| LMArena Text | 1054 | 1115 |
| LMArena Creative Writing | 1089 | 1075 |
| LMArena Multi-Turn | 1013 | 1088 |
Frequently asked questions
Is Falcon-180B better than Llama 2-70B?
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 2-70B share?
16 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Llama 2-70B has 35.