Model comparison
Claude 2 vs Gemma 2 9B
Gemma 2 9B is the stronger model overall, scoring 25.7 to 24.7 on the Noometry Index.
Last verified . 5 shared benchmarks.
GoogleSummary
- They share 5 benchmarks with published results for both. Claude 2 scores higher in 2 categories and Gemma 2 9B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude 2 leads 17.0 to 9.7.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for Claude 2 and 21% for Gemma 2 9B.
- Gemma 2 9B has downloadable open weights; the other is API-only.
Side by side
| Claude 2 | Gemma 2 9B | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 24.7 | 25.7 |
| Released | 2023-07-11 | 2024-06-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 8 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 2: —, Gemma 2 9B: 29.0 (#299)
| Benchmark | Claude 2 | Gemma 2 9B |
|---|---|---|
| BigCodeBench Instruct | — | 34.7% |
| LiveBench Coding | — | 22.5% |
| LMArena Coding | — | 1174 |
| BigCodeBench Complete | — | 40.6% |
| HumanEval+ | 61.6% | — |
Reasoning Claude 2 leads
Claude 2: 20.8 (#213), Gemma 2 9B: 15.3 (#306)
| Benchmark | Claude 2 | Gemma 2 9B |
|---|---|---|
| Epoch Capabilities Index | 120.08 | 119.78 |
| LiveBench Reasoning | — | 15.2% |
| LMArena Hard Prompts | — | 1172 |
| DTBench | 51.9% | — |
| LiveBench Data Analysis | — | 36.4% |
| LiveBench | — | 28.7% |
| PIQA | — | 83.7% |
Math Too close to call
Claude 2: 8.7 (#314), Gemma 2 9B: 9.3 (#312)
| Benchmark | Claude 2 | Gemma 2 9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 0.6% |
| MATH Level 5 | 11.7% | 21% |
| LiveBench Math | — | 19.8% |
| LMArena Math | — | 1183 |
| GSM8K | — | 84.9% |
Knowledge Claude 2 leads
Claude 2: 17.0 (#282), Gemma 2 9B: 9.7 (#300)
| Benchmark | Claude 2 | Gemma 2 9B |
|---|---|---|
| GPQA Diamond | 34.7% | 27.5% |
| MMLU | 78.5% | 72.1% |
| LMArena Expert | — | 1147 |
| BoolQ | — | 85.7% |
| TriviaQA | 87.5% | — |
Multilingual Not comparable
Claude 2: —, Gemma 2 9B: 36.8 (#233)
| Benchmark | Claude 2 | Gemma 2 9B |
|---|---|---|
| LMArena Non-English | — | 1188 |
| LMArena Chinese | — | 1185 |
| LMArena French | — | 1189 |
| LMArena German | — | 1186 |
| LMArena Japanese | — | 1144 |
| LMArena Korean | — | 1137 |
| LMArena Russian | — | 1200 |
| LMArena Spanish | — | 1200 |
Instruction Following Not comparable
Claude 2: —, Gemma 2 9B: 57.8 (#264)
| Benchmark | Claude 2 | Gemma 2 9B |
|---|---|---|
| LiveBench Instruction Following | — | 52.6% |
| LMArena Instruction Following | — | 1178 |
Long Context Not comparable
Claude 2: —, Gemma 2 9B: 36.3 (#228)
| Benchmark | Claude 2 | Gemma 2 9B |
|---|---|---|
| LMArena Longer Query | — | 1197 |
Writing & Preference Not comparable
Claude 2: —, Gemma 2 9B: 32.3 (#276)
| Benchmark | Claude 2 | Gemma 2 9B |
|---|---|---|
| LMArena Text | — | 1207 |
| LMArena Creative Writing | — | 1206 |
| EQ-Bench Creative Writing | — | 841 |
| LMArena Multi-Turn | — | 1193 |
| LiveBench Language | — | 25.5% |
Frequently asked questions
Is Claude 2 better than Gemma 2 9B?
Gemma 2 9B is the stronger model overall, scoring 25.7 to 24.7 on the Noometry Index.
How many benchmarks do Claude 2 and Gemma 2 9B share?
5 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Gemma 2 9B has 35.