Model comparison
Gemma 3 4B vs GPT-5.1
GPT-5.1 is the stronger model overall, scoring 49.0 to 28.1 on the Noometry Index. Gemma 3 4B costs 69× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
GoogleSummary
- They share 19 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and GPT-5.1 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.1 leads 50.6 to 11.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.5% for Gemma 3 4B and 88.6% for GPT-5.1.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- GPT-5.1 accepts more context: 400K tokens versus 131K.
- Gemma 3 4B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 4B | GPT-5.1 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 28.1 | 49.0 |
| Released | 2025-03-12 | 2025-11-13 |
| Weights | Open | Proprietary |
| Context window | 131K | 400K |
| Max output | 4K | 128K |
| Input $ / M tokens | $0.04 | $1.25 |
| Output $ / M tokens | $0.08 | $10 |
| Results tracked | 22 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
Gemma 3 4B: 35.9 (#215), GPT-5.1: 46.4 (#66)
| Benchmark | Gemma 3 4B | GPT-5.1 |
|---|---|---|
| LMArena Coding | 1230 | 1454 |
| SWE-bench Verified | — | 68% |
| SWE-bench Verified (bash only) | — | 66% |
| LMArena WebDev | — | 1395 |
| SciCode | — | 43.3% |
| GSO | — | 13.7% |
| WeirdML | — | 60.8% |
| LiveBench Coding | — | 72.5% |
| ALE-Bench | — | 1,192 |
Agentic & Tool Use GPT-5.1 leads
Gemma 3 4B: 20.9 (#142), GPT-5.1: 32.7 (#60)
| Benchmark | Gemma 3 4B | GPT-5.1 |
|---|---|---|
| Terminal-Bench | — | 47.6% |
| Berkeley Function Calling Leaderboard | 19.6% | — |
| DeepResearch Bench | — | 42.8% |
| LMArena Search | — | 1199 |
| Vending-Bench 2 | — | 1,473 |
Reasoning GPT-5.1 leads
Gemma 3 4B: 13.2 (#335), GPT-5.1: 39.8 (#58)
| Benchmark | Gemma 3 4B | GPT-5.1 |
|---|---|---|
| Chess Puzzles | 0% | 32% |
| LMArena Hard Prompts | 1253 | 1457 |
| DTBench | 50.9% | 90.1% |
| LMCA | 2.8% | 43.9% |
| Epoch Capabilities Index | 116.02 | 149.64 |
| ARC-AGI-2 | — | 17.6% |
| SimpleBench | — | 53.2% |
| Kagi LLM Benchmark | 25.2% | — |
| ARC-AGI-1 | — | 72.8% |
| CritPt | — | 4.9% |
| EnigmaEval | — | 11.2% |
| LiveBench Reasoning | — | 95.8% |
| Mystery Game Puzzles | — | 19% |
| LiveBench Data Analysis | — | 72.1% |
| ForecastBench | — | 58.1 |
| LiveBench | — | 78.8% |
Math GPT-5.1 leads
Gemma 3 4B: 16.8 (#292), GPT-5.1: 52.2 (#51)
| Benchmark | Gemma 3 4B | GPT-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | 88.6% |
| LMArena Math | 1239 | 1447 |
| Omni-MATH | — | 46.4% |
| LiveBench Math | — | 94.5% |
| FrontierMath (Feb 2025 set) | — | 31% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge GPT-5.1 leads
Gemma 3 4B: 11.8 (#299), GPT-5.1: 50.6 (#71)
| Benchmark | Gemma 3 4B | GPT-5.1 |
|---|---|---|
| GPQA Diamond | 23.2% | 87.6% |
| Vectara Hallucination Rate | 6.4% | 10.9% |
| LMArena Expert | 1223 | 1470 |
| Humanity's Last Exam | — | 23.7% |
| SimpleQA Verified | — | 48% |
| MMLU-Pro | — | 57.9% |
| GPQA (HELM) | — | 44.2% |
Multimodal Not comparable
Gemma 3 4B: —, GPT-5.1: 44.8 (#19)
| Benchmark | Gemma 3 4B | GPT-5.1 |
|---|---|---|
| LMArena Vision | — | 1250 |
| VPCT | — | 58.7% |
| LMArena Document | — | 1403 |
Multilingual GPT-5.1 leads
Gemma 3 4B: 42.5 (#194), GPT-5.1: 53.8 (#56)
| Benchmark | Gemma 3 4B | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1273 | 1431 |
| LMArena German | 1281 | 1438 |
| LMArena Russian | 1294 | 1435 |
| LMArena Chinese | — | 1495 |
| LMArena French | — | 1450 |
| LMArena Japanese | — | 1453 |
| LMArena Korean | — | 1401 |
| LMArena Spanish | — | 1433 |
Instruction Following GPT-5.1 leads
Gemma 3 4B: 65.2 (#225), GPT-5.1: 83.9 (#1)
| Benchmark | Gemma 3 4B | GPT-5.1 |
|---|---|---|
| LMArena Instruction Following | 1239 | 1443 |
| LiveBench Instruction Following | — | 93.3% |
| IFEval | — | 93.5% |
Long Context GPT-5.1 leads
Gemma 3 4B: 38.7 (#194), GPT-5.1: 47.6 (#14)
| Benchmark | Gemma 3 4B | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1273 | 1447 |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |
Writing & Preference GPT-5.1 leads
Gemma 3 4B: 42.0 (#239), GPT-5.1: 64.5 (#55)
| Benchmark | Gemma 3 4B | GPT-5.1 |
|---|---|---|
| LMArena Text | 1291 | 1443 |
| LMArena Creative Writing | 1271 | 1427 |
| LMArena Multi-Turn | 1255 | 1450 |
| EQ-Bench Creative Writing | 1068 | — |
| WildBench | — | 86.3% |
| LiveBench Language | — | 80.2% |
Frequently asked questions
Is Gemma 3 4B better than GPT-5.1?
GPT-5.1 is the stronger model overall, scoring 49.0 to 28.1 on the Noometry Index. Gemma 3 4B costs 69× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 4B or GPT-5.1?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; GPT-5.1 lists at $1.25 and $10.
Is Gemma 3 4B or GPT-5.1 better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 35.9 in the Noometry coding category.
Which has the bigger context window?
GPT-5.1 does, with 400K tokens against 131K.
How many benchmarks do Gemma 3 4B and GPT-5.1 share?
19 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and GPT-5.1 has 63.