Model comparison
Falcon-180B vs Llama 3-8B
Falcon-180B is the stronger model overall, scoring 32.2 to 25.5 on the Noometry Index.
Last verified . 11 shared benchmarks.
Technology Innovation Institute
MetaSummary
- They share 11 benchmarks with published results for both. Falcon-180B scores higher in 1 category and Llama 3-8B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 3-8B leads 37.5 to 29.1.
Side by side
| Falcon-180B | Llama 3-8B | |
|---|---|---|
| Provider | Technology Innovation Institute | Meta |
| Noometry Index | 32.2 | 25.5 |
| Released | 2023-09-06 | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Llama 3-8B: 31.0 (#289)
| Benchmark | Falcon-180B | Llama 3-8B |
|---|---|---|
| BigCodeBench Instruct | — | 31.9% |
| LMArena Coding | — | 1152 |
| BigCodeBench Complete | — | 36.9% |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 54.8% |
Reasoning Falcon-180B leads
Falcon-180B: 19.1 (#269), Llama 3-8B: 14.3 (#326)
| Benchmark | Falcon-180B | Llama 3-8B |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1133 |
| Epoch Capabilities Index | 112.13 | 116.45 |
| WinoGrande | 87.1% | 75.7% |
| Chess Puzzles | — | 0% |
| DTBench | — | 43.9% |
| Adversarial NLI | — | 57.3% |
| ForecastBench | — | 58.6 |
| HellaSwag | 89% | — |
| LAMBADA | 79.8% | — |
| PIQA | 84.9% | — |
Math Not comparable
Falcon-180B: —, Llama 3-8B: 8.8 (#323)
| Benchmark | Falcon-180B | Llama 3-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 1.9% |
| LMArena Math | — | 1151 |
| MATH Level 5 | — | 6.1% |
| GSM8K | 54.4% | — |
Knowledge Not comparable
Falcon-180B: —, Llama 3-8B: 7.8 (#308)
| Benchmark | Falcon-180B | Llama 3-8B |
|---|---|---|
| ARC (AI2) Challenge | 67.8% | 82.8% |
| MMLU | 70.6% | 68.8% |
| OpenBookQA | 64.2% | 82.6% |
| GPQA Diamond | — | 26.1% |
| LMArena Expert | — | 1113 |
| BoolQ | 89% | — |
| TriviaQA | — | 67.7% |
Multilingual Llama 3-8B leads
Falcon-180B: 25.2 (#286), Llama 3-8B: 30.8 (#261)
| Benchmark | Falcon-180B | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 1000 | 1098 |
| LMArena Chinese | — | 1076 |
| LMArena French | — | 1159 |
| LMArena German | — | 1104 |
| LMArena Japanese | — | 967 |
| LMArena Korean | — | 1004 |
| LMArena Russian | — | 1109 |
| LMArena Spanish | — | 1173 |
Instruction Following Llama 3-8B leads
Falcon-180B: 53.4 (#286), Llama 3-8B: 58.4 (#260)
| Benchmark | Falcon-180B | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1047 | 1127 |
Long Context Not comparable
Falcon-180B: —, Llama 3-8B: 34.2 (#251)
| Benchmark | Falcon-180B | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | — | 1128 |
Writing & Preference Llama 3-8B leads
Falcon-180B: 29.1 (#295), Llama 3-8B: 37.5 (#256)
| Benchmark | Falcon-180B | Llama 3-8B |
|---|---|---|
| LMArena Text | 1054 | 1166 |
| LMArena Creative Writing | 1089 | 1150 |
| LMArena Multi-Turn | 1013 | 1152 |
Frequently asked questions
Is Falcon-180B better than Llama 3-8B?
Falcon-180B is the stronger model overall, scoring 32.2 to 25.5 on the Noometry Index.
How many benchmarks do Falcon-180B and Llama 3-8B share?
11 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Llama 3-8B has 34.