Model comparison
Falcon-180B vs Llama 3-70B
Falcon-180B is the stronger model overall, scoring 31.8 to 28.5 on the Noometry Index.
Last verified . 9 shared benchmarks.
Technology Innovation Institute
MetaSummary
- They share 9 benchmarks with published results for both. Falcon-180B scores higher in 1 category and Llama 3-70B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 3-70B leads 43.0 to 29.3.
Side by side
| Falcon-180B | Llama 3-70B | |
|---|---|---|
| Provider | Technology Innovation Institute | Meta |
| Noometry Index | 31.8 | 28.5 |
| Released | 2023-09-06 | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Llama 3-70B: 35.3 (#215)
| Benchmark | Falcon-180B | Llama 3-70B |
|---|---|---|
| BigCodeBench Instruct | — | 43.6% |
| LMArena Coding | — | 1206 |
| BigCodeBench Complete | — | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
Falcon-180B: —, Llama 3-70B: 20.9 (#132)
| Benchmark | Falcon-180B | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Too close to call
Falcon-180B: 18.3 (#266), Llama 3-70B: 17.4 (#284)
| Benchmark | Falcon-180B | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1195 |
| Epoch Capabilities Index | 111.89 | 122.91 |
| WinoGrande | 87.1% | 83.5% |
| Kagi LLM Benchmark | — | 35.1% |
| DTBench | — | 54.2% |
| ForecastBench | — | 57.1 |
| HellaSwag | 89% | — |
| LAMBADA | 79.8% | — |
| PIQA | 84.9% | — |
Math Not comparable
Falcon-180B: —, Llama 3-70B: 12.0 (#299)
| Benchmark | Falcon-180B | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| LMArena Math | — | 1218 |
| MATH Level 5 | — | 22.6% |
| GSM8K | 54.4% | — |
Knowledge Not comparable
Falcon-180B: —, Llama 3-70B: 20.8 (#272)
| Benchmark | Falcon-180B | Llama 3-70B |
|---|---|---|
| MMLU | 70.6% | 79.3% |
| GPQA Diamond | — | 40.6% |
| LMArena Expert | — | 1149 |
| ARC (AI2) Challenge | 67.8% | — |
| BoolQ | 89% | — |
| OpenBookQA | 64.2% | — |
Multilingual Llama 3-70B leads
Falcon-180B: 25.3 (#281), Llama 3-70B: 33.8 (#246)
| Benchmark | Falcon-180B | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1000 | 1142 |
| LMArena Chinese | — | 1114 |
| LMArena French | — | 1231 |
| LMArena German | — | 1169 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Russian | — | 1159 |
| LMArena Spanish | — | 1241 |
Instruction Following Llama 3-70B leads
Falcon-180B: 53.6 (#281), Llama 3-70B: 62.8 (#233)
| Benchmark | Falcon-180B | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1047 | 1194 |
Long Context Not comparable
Falcon-180B: —, Llama 3-70B: 35.6 (#235)
| Benchmark | Falcon-180B | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | — | 1174 |
Writing & Preference Llama 3-70B leads
Falcon-180B: 29.3 (#290), Llama 3-70B: 43.0 (#225)
| Benchmark | Falcon-180B | Llama 3-70B |
|---|---|---|
| LMArena Text | 1054 | 1221 |
| LMArena Creative Writing | 1089 | 1210 |
| LMArena Multi-Turn | 1013 | 1223 |
Frequently asked questions
Is Falcon-180B better than Llama 3-70B?
Falcon-180B is the stronger model overall, scoring 31.8 to 28.5 on the Noometry Index.
How many benchmarks do Falcon-180B and Llama 3-70B share?
9 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Llama 3-70B has 31.