Model comparison
Gemma 2 27B vs GPT-5.4 mini
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 29.4 on the Noometry Index. Gemma 2 27B costs 2.6× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
GoogleSummary
- They share 22 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and GPT-5.4 mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 mini leads 45.5 to 10.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.4% for Gemma 2 27B and 88.9% for GPT-5.4 mini.
- Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- GPT-5.4 mini accepts more context: 400K tokens versus 8K.
- Gemma 2 27B has downloadable open weights; the other is API-only.
Side by side
| Gemma 2 27B | GPT-5.4 mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 29.4 | 45.0 |
| Released | 2024-06-24 | 2026-03-17 |
| Weights | Open | Proprietary |
| Context window | 8K | 400K |
| Max output | 2K | 128K |
| Input $ / M tokens | $0.65 | $0.75 |
| Output $ / M tokens | $0.65 | $4.50 |
| Results tracked | 34 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
Gemma 2 27B: 34.1 (#246), GPT-5.4 mini: 45.2 (#72)
| Benchmark | Gemma 2 27B | GPT-5.4 mini |
|---|---|---|
| LMArena Coding | 1211 | 1438 |
| FrontierCode | — | 27% |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| WeirdML | — | 60.3% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Not comparable
Gemma 2 27B: —, GPT-5.4 mini: 29.9 (#81)
| Benchmark | Gemma 2 27B | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | — | 36.3% |
Reasoning GPT-5.4 mini leads
Gemma 2 27B: 15.3 (#315), GPT-5.4 mini: 30.4 (#85)
| Benchmark | Gemma 2 27B | GPT-5.4 mini |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1424 |
| DTBench | 48% | 80% |
| LMCA | 7.1% | 40.8% |
| Epoch Capabilities Index | 122.08 | 148.84 |
| ARC-AGI-2 | — | 18.9% |
| Kagi LLM Benchmark | — | 37.9% |
| NYT Connections (extended) | — | 61.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 10% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 61.7% |
| LiveBench Reasoning | 28.1% | — |
| Mystery Game Puzzles | — | 11% |
| LiveBench Data Analysis | 47.9% | — |
| ForecastBench | — | 57 |
| LiveBench | 38.2% | — |
Math GPT-5.4 mini leads
Gemma 2 27B: 10.7 (#311), GPT-5.4 mini: 45.5 (#75)
| Benchmark | Gemma 2 27B | GPT-5.4 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 88.9% |
| LMArena Math | 1212 | 1419 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| ProofBench | — | 21% |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GPT-5.4 mini leads
Gemma 2 27B: 19.0 (#280), GPT-5.4 mini: 51.5 (#67)
| Benchmark | Gemma 2 27B | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 36.5% | 86.9% |
| LMArena Expert | 1172 | 1435 |
| SimpleQA Verified | — | 29.4% |
| Confabulations | 27.1% | — |
| Vectara Hallucination Rate | — | 5.5% |
| MMLU | 75.7% | — |
Multimodal Not comparable
Gemma 2 27B: —, GPT-5.4 mini: 39.7 (#56)
| Benchmark | Gemma 2 27B | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual GPT-5.4 mini leads
Gemma 2 27B: 38.6 (#226), GPT-5.4 mini: 51.9 (#96)
| Benchmark | Gemma 2 27B | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1217 | 1405 |
| LMArena Chinese | 1221 | 1446 |
| LMArena French | 1247 | 1440 |
| LMArena German | 1209 | 1409 |
| LMArena Japanese | 1175 | 1374 |
| LMArena Korean | 1174 | 1368 |
| LMArena Russian | 1234 | 1417 |
| LMArena Spanish | 1228 | 1405 |
Instruction Following GPT-5.4 mini leads
Gemma 2 27B: 60.5 (#249), GPT-5.4 mini: 74.1 (#102)
| Benchmark | Gemma 2 27B | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1206 | 1405 |
| LiveBench Instruction Following | 58.1% | — |
Long Context GPT-5.4 mini leads
Gemma 2 27B: 37.3 (#218), GPT-5.4 mini: 43.0 (#112)
| Benchmark | Gemma 2 27B | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1231 | 1407 |
Writing & Preference GPT-5.4 mini leads
Gemma 2 27B: 44.2 (#225), GPT-5.4 mini: 64.0 (#58)
| Benchmark | Gemma 2 27B | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1231 | 1412 |
| LMArena Creative Writing | 1241 | 1370 |
| LMArena Multi-Turn | 1224 | 1429 |
| EQ-Bench Creative Writing | — | 1665 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than GPT-5.4 mini?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 29.4 on the Noometry Index. Gemma 2 27B costs 2.6× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Which is cheaper, Gemma 2 27B or GPT-5.4 mini?
Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is Gemma 2 27B or GPT-5.4 mini better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 mini does, with 400K tokens against 8K.
How many benchmarks do Gemma 2 27B and GPT-5.4 mini share?
22 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and GPT-5.4 mini has 46.