Model comparison
Claude 2 vs Gemma 2B
Gemma 2B is the stronger model overall, scoring 29.6 to 25.0 on the Noometry Index.
Last verified . 4 shared benchmarks.
GoogleSummary
- They share 4 benchmarks with published results for both. Claude 2 scores higher in 1 category and Gemma 2B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 2B leads 30.0 to 9.3.
- Gemma 2B has downloadable open weights; the other is API-only.
Side by side
| Claude 2 | Gemma 2B | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 25.0 | 29.6 |
| Released | 2023-07-11 | 2024-02-21 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 8 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 2: —, Gemma 2B: 29.4 (#305)
| Benchmark | Claude 2 | Gemma 2B |
|---|---|---|
| HumanEval+ | 61.6% | 20.7% |
| LMArena Coding | — | 1010 |
| MBPP+ | — | 34.1% |
Reasoning Claude 2 leads
Claude 2: 21.7 (#216), Gemma 2B: 18.8 (#275)
| Benchmark | Claude 2 | Gemma 2B |
|---|---|---|
| Epoch Capabilities Index | 120.13 | 94.2 |
| LMArena Hard Prompts | — | 989 |
| DTBench | 51.9% | — |
| BIG-Bench Hard | — | 35.2% |
| HellaSwag | — | 71.4% |
| PIQA | — | 77.3% |
| WinoGrande | — | 65.4% |
Math Gemma 2B leads
Claude 2: 9.3 (#320), Gemma 2B: 30.0 (#239)
| Benchmark | Claude 2 | Gemma 2B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LMArena Math | — | 1009 |
| MATH Level 5 | 11.7% | — |
| GSM8K | — | 17.7% |
Knowledge Not comparable
Claude 2: 16.9 (#287), Gemma 2B: —
| Benchmark | Claude 2 | Gemma 2B |
|---|---|---|
| MMLU | 78.5% | 42.3% |
| TriviaQA | 87.5% | 53.2% |
| GPQA Diamond | 34.7% | — |
| ARC (AI2) Challenge | — | 42.1% |
| BoolQ | — | 69.4% |
Multilingual Not comparable
Claude 2: —, Gemma 2B: 23.0 (#294)
| Benchmark | Claude 2 | Gemma 2B |
|---|---|---|
| LMArena Non-English | — | 958 |
| LMArena Chinese | — | 986 |
| LMArena Russian | — | 937 |
Instruction Following Not comparable
Claude 2: —, Gemma 2B: 48.5 (#302)
| Benchmark | Claude 2 | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | — | 970 |
Long Context Not comparable
Claude 2: —, Gemma 2B: 29.9 (#291)
| Benchmark | Claude 2 | Gemma 2B |
|---|---|---|
| LMArena Longer Query | — | 981 |
Writing & Preference Not comparable
Claude 2: —, Gemma 2B: 24.0 (#308)
| Benchmark | Claude 2 | Gemma 2B |
|---|---|---|
| LMArena Text | — | 1002 |
| LMArena Creative Writing | — | 987 |
| LMArena Multi-Turn | — | 945 |
Frequently asked questions
Is Claude 2 better than Gemma 2B?
Gemma 2B is the stronger model overall, scoring 29.6 to 25.0 on the Noometry Index.
How many benchmarks do Claude 2 and Gemma 2B share?
4 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Gemma 2B has 23.