Model comparison
Gemma 2 9B vs Llama 3.1-8B
Gemma 2 9B is the stronger model overall, scoring 25.9 to 23.0 on the Noometry Index.
Last verified . 28 shared benchmarks.
Google
MetaSummary
- They share 28 benchmarks with published results for both. Gemma 2 9B scores higher in 6 categories and Llama 3.1-8B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemma 2 9B leads 29.4 to 20.2.
Side by side
| Gemma 2 9B | Llama 3.1-8B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 25.9 | 23.0 |
| Released | 2024-06-24 | 2024-07-23 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.08 |
| Results tracked | 35 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 9B leads
Gemma 2 9B: 29.4 (#304), Llama 3.1-8B: 20.2 (#340)
| Benchmark | Gemma 2 9B | Llama 3.1-8B |
|---|---|---|
| BigCodeBench Instruct | 34.7% | 32.8% |
| LMArena Coding | 1173 | 1195 |
| BigCodeBench Complete | 40.6% | 40.5% |
| SciCode | — | 13.2% |
| WeirdML | — | 1.7% |
| LiveBench Coding | 22.5% | — |
| HumanEval+ | — | 62.8% |
| MBPP+ | — | 55.6% |
Agentic & Tool Use Not comparable
Gemma 2 9B: —, Llama 3.1-8B: 22.5 (#131)
| Benchmark | Gemma 2 9B | Llama 3.1-8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 25.8% |
| BALROG | — | 15.1% |
Reasoning Gemma 2 9B leads
Gemma 2 9B: 15.9 (#309), Llama 3.1-8B: 14.9 (#321)
| Benchmark | Gemma 2 9B | Llama 3.1-8B |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1175 |
| Epoch Capabilities Index | 119.83 | 116.57 |
| PIQA | 83.7% | 81.2% |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 15.2% | — |
| DTBench | — | 50.9% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 5.4% |
| LiveBench | 28.7% | — |
Math Too close to call
Gemma 2 9B: 9.9 (#318), Llama 3.1-8B: 10.2 (#317)
| Benchmark | Gemma 2 9B | Llama 3.1-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 1.7% |
| LMArena Math | 1183 | 1179 |
| MATH Level 5 | 21% | 22.9% |
| GSM8K | 84.9% | 82.4% |
| Omni-MATH | — | 13.7% |
| LiveBench Math | 19.8% | — |
Knowledge Gemma 2 9B leads
Gemma 2 9B: 9.7 (#305), Llama 3.1-8B: 8.0 (#307)
| Benchmark | Gemma 2 9B | Llama 3.1-8B |
|---|---|---|
| GPQA Diamond | 27.5% | 27% |
| LMArena Expert | 1147 | 1144 |
| BoolQ | 85.7% | 82.8% |
| MMLU | 72.1% | 56.1% |
| MMLU-Pro | — | 40.6% |
| GPQA (HELM) | — | 24.7% |
Multilingual Gemma 2 9B leads
Gemma 2 9B: 36.6 (#238), Llama 3.1-8B: 34.0 (#249)
| Benchmark | Gemma 2 9B | Llama 3.1-8B |
|---|---|---|
| LMArena Non-English | 1188 | 1148 |
| LMArena Chinese | 1185 | 1151 |
| LMArena French | 1190 | 1177 |
| LMArena German | 1186 | 1144 |
| LMArena Japanese | 1144 | 1061 |
| LMArena Korean | 1137 | 1053 |
| LMArena Russian | 1200 | 1158 |
| LMArena Spanish | 1200 | 1169 |
Instruction Following Llama 3.1-8B leads
Gemma 2 9B: 57.6 (#269), Llama 3.1-8B: 58.9 (#258)
| Benchmark | Gemma 2 9B | Llama 3.1-8B |
|---|---|---|
| LMArena Instruction Following | 1178 | 1159 |
| LiveBench Instruction Following | 52.6% | — |
| IFEval | — | 74.3% |
Long Context Too close to call
Gemma 2 9B: 36.3 (#233), Llama 3.1-8B: 35.8 (#238)
| Benchmark | Gemma 2 9B | Llama 3.1-8B |
|---|---|---|
| LMArena Longer Query | 1197 | 1182 |
Writing & Preference Gemma 2 9B leads
Gemma 2 9B: 32.1 (#281), Llama 3.1-8B: 29.7 (#290)
| Benchmark | Gemma 2 9B | Llama 3.1-8B |
|---|---|---|
| LMArena Text | 1207 | 1187 |
| LMArena Creative Writing | 1206 | 1154 |
| EQ-Bench Creative Writing | 841 | 713 |
| LMArena Multi-Turn | 1193 | 1172 |
| WildBench | — | 68.7% |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Llama 3.1-8B?
Gemma 2 9B is the stronger model overall, scoring 25.9 to 23.0 on the Noometry Index.
Is Gemma 2 9B or Llama 3.1-8B better for coding?
Gemma 2 9B scores higher on coding benchmarks: 29.4 versus 20.2 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Llama 3.1-8B share?
28 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Llama 3.1-8B has 43.