Model comparison
Gemini 1.5 Pro (May 2024) vs Gemma 2 9B
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 25.9 on the Noometry Index.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 7 categories and Gemma 2 9B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 1.5 Pro (May 2024) leads 52.4 to 32.1.
- The biggest single-benchmark swing is MATH Level 5: 70.4% for Gemini 1.5 Pro (May 2024) and 21% for Gemma 2 9B.
- Gemma 2 9B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Gemma 2 9B | |
|---|---|---|
| Provider | ||
| Noometry Index | 32.1 | 25.9 |
| Released | 2024-02-15 | 2024-06-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 45 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), Gemma 2 9B: 29.4 (#304)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 2 9B |
|---|---|---|
| BigCodeBench Instruct | 43.8% | 34.7% |
| LMArena Coding | 1294 | 1173 |
| BigCodeBench Complete | 57.5% | 40.6% |
| WeirdML | 22.2% | — |
| LiveBench Coding | — | 22.5% |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Pro (May 2024): 17.9 (#145), Gemma 2 9B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 2 9B |
|---|---|---|
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning Gemma 2 9B leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Gemma 2 9B: 15.9 (#309)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 2 9B |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1171 |
| Epoch Capabilities Index | 131.73 | 119.83 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| LiveBench Reasoning | — | 15.2% |
| DTBench | 59% | — |
| LiveBench Data Analysis | — | 36.4% |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
| LiveBench | — | 28.7% |
| PIQA | — | 83.7% |
Math Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Gemma 2 9B: 9.9 (#318)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 2 9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 0.6% |
| LMArena Math | 1315 | 1183 |
| MATH Level 5 | 70.4% | 21% |
| Omni-MATH | 36.4% | — |
| LiveBench Math | — | 19.8% |
| GSM8K | — | 84.9% |
Knowledge Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Gemma 2 9B: 9.7 (#305)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 2 9B |
|---|---|---|
| GPQA Diamond | 57.2% | 27.5% |
| LMArena Expert | 1279 | 1147 |
| MMLU | 86.9% | 72.1% |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
| BoolQ | — | 85.7% |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), Gemma 2 9B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 2 9B |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Gemma 2 9B: 36.6 (#238)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 2 9B |
|---|---|---|
| LMArena Non-English | 1312 | 1188 |
| LMArena Chinese | 1331 | 1185 |
| LMArena French | 1302 | 1190 |
| LMArena German | 1286 | 1186 |
| LMArena Japanese | 1292 | 1144 |
| LMArena Korean | 1298 | 1137 |
| LMArena Russian | 1320 | 1200 |
| LMArena Spanish | 1311 | 1200 |
Instruction Following Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Gemma 2 9B: 57.6 (#269)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 2 9B |
|---|---|---|
| LMArena Instruction Following | 1297 | 1178 |
| LiveBench Instruction Following | — | 52.6% |
| IFEval | 83.7% | — |
Long Context Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Gemma 2 9B: 36.3 (#233)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 2 9B |
|---|---|---|
| LMArena Longer Query | 1308 | 1197 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Gemma 2 9B: 32.1 (#281)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 2 9B |
|---|---|---|
| LMArena Text | 1319 | 1207 |
| LMArena Creative Writing | 1333 | 1206 |
| LMArena Multi-Turn | 1296 | 1193 |
| EQ-Bench Creative Writing | — | 841 |
| WildBench | 81.3% | — |
| LiveBench Language | — | 25.5% |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Gemma 2 9B?
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 25.9 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Gemma 2 9B better for coding?
Gemini 1.5 Pro (May 2024) scores higher on coding benchmarks: 34.2 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Gemma 2 9B share?
24 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Gemma 2 9B has 35.