Model comparison
Falcon-180B vs Gemma 2 27B
Falcon-180B is the stronger model overall, scoring 32.2 to 29.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
Technology Innovation Institute
GoogleSummary
- They share 8 benchmarks with published results for both. Falcon-180B scores higher in 1 category and Gemma 2 27B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 2 27B leads 44.2 to 29.1.
Side by side
| Falcon-180B | Gemma 2 27B | |
|---|---|---|
| Provider | Technology Innovation Institute | |
| Noometry Index | 32.2 | 29.4 |
| Released | 2023-09-06 | 2024-06-24 |
| Weights | Open | Open |
| Context window | — | 8K |
| Max output | — | 2K |
| Input $ / M tokens | — | $0.65 |
| Output $ / M tokens | — | $0.65 |
| Results tracked | 16 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Gemma 2 27B: 34.1 (#246)
| Benchmark | Falcon-180B | Gemma 2 27B |
|---|---|---|
| BigCodeBench Instruct | — | 42.8% |
| LiveBench Coding | — | 36% |
| LMArena Coding | — | 1211 |
| BigCodeBench Complete | — | 52.5% |
Reasoning Falcon-180B leads
Falcon-180B: 19.1 (#269), Gemma 2 27B: 15.3 (#315)
| Benchmark | Falcon-180B | Gemma 2 27B |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1198 |
| Epoch Capabilities Index | 112.13 | 122.08 |
| LiveBench Reasoning | — | 28.1% |
| DTBench | — | 48% |
| LiveBench Data Analysis | — | 47.9% |
| LMCA | — | 7.1% |
| HellaSwag | 89% | — |
| LAMBADA | 79.8% | — |
| LiveBench | — | 38.2% |
| PIQA | 84.9% | — |
| WinoGrande | 87.1% | — |
Math Not comparable
Falcon-180B: —, Gemma 2 27B: 10.7 (#311)
| Benchmark | Falcon-180B | Gemma 2 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 1.4% |
| LiveBench Math | — | 26.5% |
| LMArena Math | — | 1212 |
| MATH Level 5 | — | 27.9% |
| GSM8K | 54.4% | — |
Knowledge Not comparable
Falcon-180B: —, Gemma 2 27B: 19.0 (#280)
| Benchmark | Falcon-180B | Gemma 2 27B |
|---|---|---|
| MMLU | 70.6% | 75.7% |
| GPQA Diamond | — | 36.5% |
| Confabulations | — | 27.1% |
| LMArena Expert | — | 1172 |
| ARC (AI2) Challenge | 67.8% | — |
| BoolQ | 89% | — |
| OpenBookQA | 64.2% | — |
Multilingual Gemma 2 27B leads
Falcon-180B: 25.2 (#286), Gemma 2 27B: 38.6 (#226)
| Benchmark | Falcon-180B | Gemma 2 27B |
|---|---|---|
| LMArena Non-English | 1000 | 1217 |
| LMArena Chinese | — | 1221 |
| LMArena French | — | 1247 |
| LMArena German | — | 1209 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1174 |
| LMArena Russian | — | 1234 |
| LMArena Spanish | — | 1228 |
Instruction Following Gemma 2 27B leads
Falcon-180B: 53.4 (#286), Gemma 2 27B: 60.5 (#249)
| Benchmark | Falcon-180B | Gemma 2 27B |
|---|---|---|
| LMArena Instruction Following | 1047 | 1206 |
| LiveBench Instruction Following | — | 58.1% |
Long Context Not comparable
Falcon-180B: —, Gemma 2 27B: 37.3 (#218)
| Benchmark | Falcon-180B | Gemma 2 27B |
|---|---|---|
| LMArena Longer Query | — | 1231 |
Writing & Preference Gemma 2 27B leads
Falcon-180B: 29.1 (#295), Gemma 2 27B: 44.2 (#225)
| Benchmark | Falcon-180B | Gemma 2 27B |
|---|---|---|
| LMArena Text | 1054 | 1231 |
| LMArena Creative Writing | 1089 | 1241 |
| LMArena Multi-Turn | 1013 | 1224 |
| LiveBench Language | — | 32.6% |
Frequently asked questions
Is Falcon-180B better than Gemma 2 27B?
Falcon-180B is the stronger model overall, scoring 32.2 to 29.4 on the Noometry Index.
How many benchmarks do Falcon-180B and Gemma 2 27B share?
8 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Gemma 2 27B has 34.