Model comparison
Falcon-180B vs Gemma 2B
Falcon-180B is the stronger model overall, scoring 31.8 to 29.1 on the Noometry Index.
Last verified . 14 shared benchmarks.
Technology Innovation Institute
GoogleSummary
- They share 14 benchmarks with published results for both. Falcon-180B scores higher in 4 categories and Gemma 2B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Falcon-180B leads 29.3 to 24.1.
Side by side
| Falcon-180B | Gemma 2B | |
|---|---|---|
| Provider | Technology Innovation Institute | |
| Noometry Index | 31.8 | 29.1 |
| Released | 2023-09-06 | 2024-02-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Gemma 2B: 28.9 (#300)
| Benchmark | Falcon-180B | Gemma 2B |
|---|---|---|
| LMArena Coding | — | 1010 |
| HumanEval+ | — | 20.7% |
| MBPP+ | — | 34.1% |
Reasoning Too close to call
Falcon-180B: 18.3 (#266), Gemma 2B: 17.9 (#275)
| Benchmark | Falcon-180B | Gemma 2B |
|---|---|---|
| LMArena Hard Prompts | 1007 | 989 |
| Epoch Capabilities Index | 111.89 | 93.57 |
| HellaSwag | 89% | 71.4% |
| PIQA | 84.9% | 77.3% |
| WinoGrande | 87.1% | 65.4% |
| BIG-Bench Hard | — | 35.2% |
| LAMBADA | 79.8% | — |
Math Not comparable
Falcon-180B: —, Gemma 2B: 27.6 (#237)
| Benchmark | Falcon-180B | Gemma 2B |
|---|---|---|
| GSM8K | 54.4% | 17.7% |
| LMArena Math | — | 1009 |
Knowledge Not comparable
Falcon-180B: —, Gemma 2B: —
| Benchmark | Falcon-180B | Gemma 2B |
|---|---|---|
| ARC (AI2) Challenge | 67.8% | 42.1% |
| BoolQ | 89% | 69.4% |
| MMLU | 70.6% | 42.3% |
| OpenBookQA | 64.2% | — |
| TriviaQA | — | 53.2% |
Multilingual Falcon-180B leads
Falcon-180B: 25.3 (#281), Gemma 2B: 23.1 (#289)
| Benchmark | Falcon-180B | Gemma 2B |
|---|---|---|
| LMArena Non-English | 1000 | 958 |
| LMArena Chinese | — | 986 |
| LMArena Russian | — | 937 |
Instruction Following Falcon-180B leads
Falcon-180B: 53.6 (#281), Gemma 2B: 48.8 (#297)
| Benchmark | Falcon-180B | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | 1047 | 971 |
Long Context Not comparable
Falcon-180B: —, Gemma 2B: 29.9 (#286)
| Benchmark | Falcon-180B | Gemma 2B |
|---|---|---|
| LMArena Longer Query | — | 981 |
Writing & Preference Falcon-180B leads
Falcon-180B: 29.3 (#290), Gemma 2B: 24.1 (#303)
| Benchmark | Falcon-180B | Gemma 2B |
|---|---|---|
| LMArena Text | 1054 | 1002 |
| LMArena Creative Writing | 1089 | 986 |
| LMArena Multi-Turn | 1013 | 945 |
Frequently asked questions
Is Falcon-180B better than Gemma 2B?
Falcon-180B is the stronger model overall, scoring 31.8 to 29.1 on the Noometry Index.
How many benchmarks do Falcon-180B and Gemma 2B share?
14 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Gemma 2B has 23.