Model comparison
Gemma 1.1 2b IT vs GPT-4
Gemma 1.1 2b IT and GPT-4 score almost the same on the Noometry Index (29.3 vs 29.1), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
GoogleSummary
- They share 15 benchmarks with published results for both. Gemma 1.1 2b IT scores higher in 3 categories and GPT-4 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 1.1 2b IT leads 30.8 to 10.8.
- Gemma 1.1 2b IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 1.1 2b IT | GPT-4 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 29.3 | 29.1 |
| Released | — | 2023-03-14 |
| Weights | Open | Proprietary |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $30 |
| Output $ / M tokens | — | $60 |
| Results tracked | 16 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4 leads
Gemma 1.1 2b IT: 30.1 (#299), GPT-4: 31.6 (#283)
| Benchmark | Gemma 1.1 2b IT | GPT-4 |
|---|---|---|
| LMArena Coding | 1034 | 1254 |
| HumanEval+ | 17.7% | 79.3% |
| WeirdML | — | 12.4% |
| BigCodeBench Instruct | — | 46% |
| BigCodeBench Complete | — | 57.2% |
| MBPP+ | 23.3% | — |
Agentic & Tool Use Not comparable
Gemma 1.1 2b IT: —, GPT-4: —
| Benchmark | Gemma 1.1 2b IT | GPT-4 |
|---|---|---|
| METR Time Horizons | — | 36.1% |
Reasoning Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 19.1 (#270), GPT-4: 17.8 (#289)
| Benchmark | Gemma 1.1 2b IT | GPT-4 |
|---|---|---|
| LMArena Hard Prompts | 1005 | 1241 |
| Chess Puzzles | — | 4% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 62.7% |
| LMCA | — | 17.1% |
| BIG-Bench Hard | — | 75.1% |
| Epoch Capabilities Index | — | 125.89 |
| ForecastBench | — | 57.8 |
| HellaSwag | — | 95.3% |
| WinoGrande | — | 87.5% |
Math Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 30.8 (#232), GPT-4: 10.8 (#309)
| Benchmark | Gemma 1.1 2b IT | GPT-4 |
|---|---|---|
| LMArena Math | 1047 | 1269 |
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| MATH Level 5 | — | 23% |
| GSM8K | — | 92% |
Knowledge Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 26.5 (#258), GPT-4: 18.4 (#282)
| Benchmark | Gemma 1.1 2b IT | GPT-4 |
|---|---|---|
| LMArena Expert | 970 | 1211 |
| GPQA Diamond | — | 35.7% |
| MMLU | — | 86.4% |
| TriviaQA | — | 84.8% |
Multilingual GPT-4 leads
Gemma 1.1 2b IT: 24.6 (#289), GPT-4: 40.6 (#215)
| Benchmark | Gemma 1.1 2b IT | GPT-4 |
|---|---|---|
| LMArena Non-English | 988 | 1246 |
| LMArena Chinese | 1012 | 1242 |
| LMArena German | 944 | 1251 |
| LMArena Korean | 899 | 1184 |
| LMArena Russian | 990 | 1251 |
| LMArena French | — | 1283 |
| LMArena Japanese | — | 1209 |
| LMArena Spanish | — | 1261 |
Instruction Following GPT-4 leads
Gemma 1.1 2b IT: 49.9 (#299), GPT-4: 65.3 (#222)
| Benchmark | Gemma 1.1 2b IT | GPT-4 |
|---|---|---|
| LMArena Instruction Following | 992 | 1241 |
Long Context GPT-4 leads
Gemma 1.1 2b IT: 30.6 (#286), GPT-4: 37.7 (#212)
| Benchmark | Gemma 1.1 2b IT | GPT-4 |
|---|---|---|
| LMArena Longer Query | 1003 | 1244 |
Writing & Preference GPT-4 leads
Gemma 1.1 2b IT: 25.1 (#306), GPT-4: 34.9 (#268)
| Benchmark | Gemma 1.1 2b IT | GPT-4 |
|---|---|---|
| LMArena Text | 1022 | 1263 |
| LMArena Creative Writing | 998 | 1244 |
| LMArena Multi-Turn | 959 | 1257 |
| EQ-Bench Creative Writing | — | 752 |
Frequently asked questions
Is Gemma 1.1 2b IT better than GPT-4?
Gemma 1.1 2b IT and GPT-4 score almost the same on the Noometry Index (29.3 vs 29.1), so choose on price, context window or the category you care about most.
Is Gemma 1.1 2b IT or GPT-4 better for coding?
GPT-4 scores higher on coding benchmarks: 31.6 versus 30.1 in the Noometry coding category.
How many benchmarks do Gemma 1.1 2b IT and GPT-4 share?
15 benchmarks have published results for both models. Gemma 1.1 2b IT has 16 scored results on Noometry and GPT-4 has 38.