Model comparison
Gemma 3 1B vs GPT-4
GPT-4 is the stronger model overall, scoring 28.9 to 20.7 on the Noometry Index.
Last verified . 3 shared benchmarks.
GoogleSummary
- They share 3 benchmarks with published results for both. Gemma 3 1B scores higher in 1 category and GPT-4 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4 leads 18.4 to 7.1.
- The biggest single-benchmark swing is GPQA Diamond: 19.9% for Gemma 3 1B and 35.7% for GPT-4.
- Gemma 3 1B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 1B | GPT-4 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 20.7 | 28.9 |
| Released | 2025-03-12 | 2023-03-14 |
| Weights | Open | Proprietary |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $30 |
| Output $ / M tokens | — | $60 |
| Results tracked | 4 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemma 3 1B: —, GPT-4: 31.2 (#277)
| Benchmark | Gemma 3 1B | GPT-4 |
|---|---|---|
| WeirdML | — | 12.4% |
| BigCodeBench Instruct | — | 46% |
| LMArena Coding | — | 1254 |
| BigCodeBench Complete | — | 57.2% |
| HumanEval+ | — | 79.3% |
Agentic & Tool Use Not comparable
Gemma 3 1B: 13.5 (#144), GPT-4: —
| Benchmark | Gemma 3 1B | GPT-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 7.2% | — |
| METR Time Horizons | — | 36.1% |
Reasoning Gemma 3 1B leads
Gemma 3 1B: 18.5 (#260), GPT-4: 17.3 (#285)
| Benchmark | Gemma 3 1B | GPT-4 |
|---|---|---|
| Chess Puzzles | 0% | 4% |
| LMArena Hard Prompts | — | 1241 |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 62.7% |
| LMCA | — | 17.1% |
| BIG-Bench Hard | — | 75.1% |
| Epoch Capabilities Index | — | 125.88 |
| ForecastBench | — | 57.8 |
| HellaSwag | — | 95.3% |
| WinoGrande | — | 87.5% |
Math Too close to call
Gemma 3 1B: 9.6 (#310), GPT-4: 10.1 (#304)
| Benchmark | Gemma 3 1B | GPT-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 1.1% |
| LMArena Math | — | 1269 |
| MATH Level 5 | — | 23% |
| GSM8K | — | 92% |
Knowledge GPT-4 leads
Gemma 3 1B: 7.1 (#309), GPT-4: 18.4 (#277)
| Benchmark | Gemma 3 1B | GPT-4 |
|---|---|---|
| GPQA Diamond | 19.9% | 35.7% |
| LMArena Expert | — | 1211 |
| MMLU | — | 86.4% |
| TriviaQA | — | 84.8% |
Multilingual Not comparable
Gemma 3 1B: —, GPT-4: 40.8 (#210)
| Benchmark | Gemma 3 1B | GPT-4 |
|---|---|---|
| LMArena Non-English | — | 1246 |
| LMArena Chinese | — | 1242 |
| LMArena French | — | 1282 |
| LMArena German | — | 1251 |
| LMArena Japanese | — | 1209 |
| LMArena Korean | — | 1184 |
| LMArena Russian | — | 1251 |
| LMArena Spanish | — | 1261 |
Instruction Following Not comparable
Gemma 3 1B: —, GPT-4: 65.5 (#217)
| Benchmark | Gemma 3 1B | GPT-4 |
|---|---|---|
| LMArena Instruction Following | — | 1241 |
Long Context Not comparable
Gemma 3 1B: —, GPT-4: 37.7 (#207)
| Benchmark | Gemma 3 1B | GPT-4 |
|---|---|---|
| LMArena Longer Query | — | 1244 |
Writing & Preference Not comparable
Gemma 3 1B: —, GPT-4: 35.0 (#263)
| Benchmark | Gemma 3 1B | GPT-4 |
|---|---|---|
| LMArena Text | — | 1263 |
| LMArena Creative Writing | — | 1244 |
| EQ-Bench Creative Writing | — | 752 |
| LMArena Multi-Turn | — | 1257 |
Frequently asked questions
Is Gemma 3 1B better than GPT-4?
GPT-4 is the stronger model overall, scoring 28.9 to 20.7 on the Noometry Index.
How many benchmarks do Gemma 3 1B and GPT-4 share?
3 benchmarks have published results for both models. Gemma 3 1B has 4 scored results on Noometry and GPT-4 has 38.