Model comparison
Gemma 2 9B vs GPT-5 Nano
GPT-5 Nano is the stronger model overall, scoring 33.5 to 25.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
GoogleSummary
- They share 21 benchmarks with published results for both. Gemma 2 9B scores higher in 1 category and GPT-5 Nano in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Nano leads 35.9 to 9.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 81.1% for GPT-5 Nano.
- Gemma 2 9B has downloadable open weights; the other is API-only.
Side by side
| Gemma 2 9B | GPT-5 Nano | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 25.9 | 33.5 |
| Released | 2024-06-24 | 2025-08-07 |
| Weights | Open | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 35 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Nano leads
Gemma 2 9B: 29.4 (#304), GPT-5 Nano: 33.6 (#254)
| Benchmark | Gemma 2 9B | GPT-5 Nano |
|---|---|---|
| LMArena Coding | 1173 | 1351 |
| SWE-bench Verified (bash only) | — | 34.8% |
| WeirdML | — | 38.1% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
| ALE-Bench | — | 718.67 |
Agentic & Tool Use Not comparable
Gemma 2 9B: —, GPT-5 Nano: 25.8 (#106)
| Benchmark | Gemma 2 9B | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | — | 21.8% |
| Berkeley Function Calling Leaderboard | — | 51.5% |
Reasoning Too close to call
Gemma 2 9B: 15.9 (#309), GPT-5 Nano: 16.3 (#306)
| Benchmark | Gemma 2 9B | GPT-5 Nano |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1328 |
| Epoch Capabilities Index | 119.83 | 139.38 |
| ARC-AGI-2 | — | 2.6% |
| Kagi LLM Benchmark | — | 62.2% |
| ARC-AGI-1 | — | 20.7% |
| Chess Puzzles | — | 27% |
| LiveBench Reasoning | 15.2% | — |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 62.7% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 7.9% |
| ForecastBench | — | 59.1 |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math GPT-5 Nano leads
Gemma 2 9B: 9.9 (#318), GPT-5 Nano: 29.4 (#241)
| Benchmark | Gemma 2 9B | GPT-5 Nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 81.1% |
| LMArena Math | 1183 | 1317 |
| MATH Level 5 | 21% | 95.2% |
| FrontierMath (Tiers 1-3) | — | 20% |
| FrontierMath Tier 4 | — | 2.4% |
| ProofBench | — | 12% |
| Omni-MATH | — | 54.6% |
| LiveBench Math | 19.8% | — |
| FrontierMath (Feb 2025 set) | — | 8.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
| GSM8K | 84.9% | — |
Knowledge GPT-5 Nano leads
Gemma 2 9B: 9.7 (#305), GPT-5 Nano: 35.9 (#178)
| Benchmark | Gemma 2 9B | GPT-5 Nano |
|---|---|---|
| GPQA Diamond | 27.5% | 69.4% |
| LMArena Expert | 1147 | 1321 |
| SimpleQA Verified | — | 11.7% |
| MMLU-Pro | — | 77.8% |
| Vectara Hallucination Rate | — | 10.5% |
| GPQA (HELM) | — | 67.9% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multimodal Not comparable
Gemma 2 9B: —, GPT-5 Nano: 31.3 (#108)
| Benchmark | Gemma 2 9B | GPT-5 Nano |
|---|---|---|
| LMArena Vision | — | 1159 |
| VPCT | — | 37.2% |
Multilingual GPT-5 Nano leads
Gemma 2 9B: 36.6 (#238), GPT-5 Nano: 45.3 (#172)
| Benchmark | Gemma 2 9B | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1188 | 1313 |
| LMArena Chinese | 1185 | 1356 |
| LMArena German | 1186 | 1327 |
| LMArena Japanese | 1144 | 1226 |
| LMArena Korean | 1137 | 1269 |
| LMArena Russian | 1200 | 1296 |
| LMArena Spanish | 1200 | 1360 |
| LMArena French | 1190 | — |
Instruction Following GPT-5 Nano leads
Gemma 2 9B: 57.6 (#269), GPT-5 Nano: 75.0 (#79)
| Benchmark | Gemma 2 9B | GPT-5 Nano |
|---|---|---|
| LMArena Instruction Following | 1178 | 1306 |
| LiveBench Instruction Following | 52.6% | — |
| IFEval | — | 93.2% |
Long Context Gemma 2 9B leads
Gemma 2 9B: 36.3 (#233), GPT-5 Nano: 31.3 (#281)
| Benchmark | Gemma 2 9B | GPT-5 Nano |
|---|---|---|
| LMArena Longer Query | 1197 | 1312 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference GPT-5 Nano leads
Gemma 2 9B: 32.1 (#281), GPT-5 Nano: 39.1 (#249)
| Benchmark | Gemma 2 9B | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1207 | 1320 |
| LMArena Creative Writing | 1206 | 1249 |
| EQ-Bench Creative Writing | 841 | 705 |
| LMArena Multi-Turn | 1193 | 1311 |
| WildBench | — | 80.6% |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than GPT-5 Nano?
GPT-5 Nano is the stronger model overall, scoring 33.5 to 25.9 on the Noometry Index.
Is Gemma 2 9B or GPT-5 Nano better for coding?
GPT-5 Nano scores higher on coding benchmarks: 33.6 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and GPT-5 Nano share?
21 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and GPT-5 Nano has 49.