Model comparison
Gemma 2B vs o3
o3 is the stronger model overall, scoring 47.5 to 29.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
GoogleSummary
- They share 12 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and o3 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where o3 leads 63.5 to 24.0.
- Gemma 2B has downloadable open weights; the other is API-only.
Side by side
| Gemma 2B | o3 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 29.6 | 47.5 |
| Released | 2024-02-21 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 23 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
Gemma 2B: 29.4 (#305), o3: 46.8 (#64)
| Benchmark | Gemma 2B | o3 |
|---|---|---|
| LMArena Coding | 1010 | 1408 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Agentic & Tool Use Not comparable
Gemma 2B: —, o3: 34.5 (#44)
| Benchmark | Gemma 2B | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning o3 leads
Gemma 2B: 18.8 (#275), o3: 32.0 (#78)
| Benchmark | Gemma 2B | o3 |
|---|---|---|
| LMArena Hard Prompts | 989 | 1402 |
| Epoch Capabilities Index | 94.2 | 146.86 |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| BIG-Bench Hard | 35.2% | — |
| ForecastBench | — | 62.5 |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math o3 leads
Gemma 2B: 30.0 (#239), o3: 50.2 (#58)
| Benchmark | Gemma 2B | o3 |
|---|---|---|
| LMArena Math | 1009 | 1426 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, o3: 54.6 (#52)
| Benchmark | Gemma 2B | o3 |
|---|---|---|
| GPQA Diamond | — | 81.8% |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |
| LMArena Expert | — | 1402 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multimodal Not comparable
Gemma 2B: —, o3: 41.4 (#36)
| Benchmark | Gemma 2B | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual o3 leads
Gemma 2B: 23.0 (#294), o3: 51.7 (#105)
| Benchmark | Gemma 2B | o3 |
|---|---|---|
| LMArena Non-English | 958 | 1401 |
| LMArena Chinese | 986 | 1437 |
| LMArena Russian | 937 | 1406 |
| LMArena French | — | 1430 |
| LMArena German | — | 1420 |
| LMArena Japanese | — | 1403 |
| LMArena Korean | — | 1370 |
| LMArena Spanish | — | 1395 |
Instruction Following o3 leads
Gemma 2B: 48.5 (#302), o3: 72.8 (#127)
| Benchmark | Gemma 2B | o3 |
|---|---|---|
| LMArena Instruction Following | 970 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
Gemma 2B: 29.9 (#291), o3: 53.3 (#6)
| Benchmark | Gemma 2B | o3 |
|---|---|---|
| LMArena Longer Query | 981 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
Gemma 2B: 24.0 (#308), o3: 63.5 (#64)
| Benchmark | Gemma 2B | o3 |
|---|---|---|
| LMArena Text | 1002 | 1410 |
| LMArena Creative Writing | 987 | 1359 |
| LMArena Multi-Turn | 945 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |
Frequently asked questions
Is Gemma 2B better than o3?
o3 is the stronger model overall, scoring 47.5 to 29.6 on the Noometry Index.
Is Gemma 2B or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and o3 share?
12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and o3 has 63.