Model comparison
Gemma 4 26B A4B IT vs GPT-5.4 nano
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 41.9 on the Noometry Index.
Last verified . 26 shared benchmarks.
GoogleSummary
- They share 26 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 7 categories and GPT-5.4 nano in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 26B A4B IT leads 47.6 to 40.9.
- The biggest single-benchmark swing is Chess Puzzles: 6% for Gemma 4 26B A4B IT and 30% for GPT-5.4 nano.
- Gemma 4 26B A4B IT is cheaper at $0.0675 / $0.23 per million input/output tokens, against $0.20 / $1.25 for GPT-5.4 nano.
- GPT-5.4 nano accepts more context: 400K tokens versus 262K.
- Gemma 4 26B A4B IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 4 26B A4B IT | GPT-5.4 nano | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 43.5 | 41.9 |
| Released | 2026-04-02 | 2026-03-17 |
| Weights | Open | Proprietary |
| Context window | 262K | 400K |
| Max output | 33K | 128K |
| Input $ / M tokens | $0.0675 | $0.20 |
| Output $ / M tokens | $0.23 | $1.25 |
| Results tracked | 28 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 nano leads
Gemma 4 26B A4B IT: 39.0 (#164), GPT-5.4 nano: 43.6 (#84)
| Benchmark | Gemma 4 26B A4B IT | GPT-5.4 nano |
|---|---|---|
| SciCode | 40% | 46.9% |
| WeirdML | 35.2% | 49.2% |
| LMArena Coding | 1447 | 1405 |
| ALE-Bench | 927.17 | 1,005 |
| LMArena WebDev | 1359 | — |
Reasoning GPT-5.4 nano leads
Gemma 4 26B A4B IT: 21.8 (#213), GPT-5.4 nano: 23.7 (#173)
| Benchmark | Gemma 4 26B A4B IT | GPT-5.4 nano |
|---|---|---|
| CritPt | 0% | 9.3% |
| Chess Puzzles | 6% | 30% |
| LMArena Hard Prompts | 1439 | 1381 |
| DTBench | 74.9% | 80.3% |
| LMCA | 29.7% | 36.9% |
| Epoch Capabilities Index | 141.85 | 145.81 |
| ARC-AGI-2 | — | 5.7% |
| Kagi LLM Benchmark | — | 39.7% |
| ARC-AGI-1 | — | 51.5% |
| Mystery Game Puzzles | — | 9% |
| ForecastBench | — | 57.3 |
Math Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 47.6 (#67), GPT-5.4 nano: 40.9 (#88)
| Benchmark | Gemma 4 26B A4B IT | GPT-5.4 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 82.2% | 87.8% |
| LMArena Math | 1470 | 1406 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 12.2% |
| ProofBench | — | 5% |
| FrontierMath (Feb 2025 set) | — | 25.9% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 45.7 (#85), GPT-5.4 nano: 41.9 (#103)
| Benchmark | Gemma 4 26B A4B IT | GPT-5.4 nano |
|---|---|---|
| GPQA Diamond | 73.2% | 78.5% |
| Vectara Hallucination Rate | 5.2% | 3.1% |
| LMArena Expert | 1447 | 1396 |
| SimpleQA Verified | — | 11.7% |
Multimodal Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 40.6 (#46), GPT-5.4 nano: 36.7 (#78)
| Benchmark | Gemma 4 26B A4B IT | GPT-5.4 nano |
|---|---|---|
| LMArena Vision | 1260 | 1196 |
Multilingual Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 53.1 (#71), GPT-5.4 nano: 48.6 (#140)
| Benchmark | Gemma 4 26B A4B IT | GPT-5.4 nano |
|---|---|---|
| LMArena Non-English | 1421 | 1359 |
| LMArena Chinese | 1495 | 1392 |
| LMArena French | 1460 | 1396 |
| LMArena Russian | 1434 | 1363 |
| LMArena Spanish | 1417 | 1371 |
| LMArena German | — | 1367 |
| LMArena Japanese | — | 1343 |
| LMArena Korean | — | 1320 |
Instruction Following Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 74.8 (#82), GPT-5.4 nano: 71.9 (#144)
| Benchmark | Gemma 4 26B A4B IT | GPT-5.4 nano |
|---|---|---|
| LMArena Instruction Following | 1420 | 1362 |
Long Context Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 43.6 (#91), GPT-5.4 nano: 41.6 (#137)
| Benchmark | Gemma 4 26B A4B IT | GPT-5.4 nano |
|---|---|---|
| LMArena Longer Query | 1428 | 1366 |
Writing & Preference Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 58.6 (#115), GPT-5.4 nano: 55.7 (#142)
| Benchmark | Gemma 4 26B A4B IT | GPT-5.4 nano |
|---|---|---|
| LMArena Text | 1434 | 1372 |
| LMArena Creative Writing | 1402 | 1314 |
| LMArena Multi-Turn | 1441 | 1382 |
| EQ-Bench Creative Writing | 1305 | — |
Frequently asked questions
Is Gemma 4 26B A4B IT better than GPT-5.4 nano?
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 41.9 on the Noometry Index.
Which is cheaper, Gemma 4 26B A4B IT or GPT-5.4 nano?
Gemma 4 26B A4B IT is cheaper. It lists at $0.0675 per million input tokens and $0.23 per million output tokens; GPT-5.4 nano lists at $0.20 and $1.25.
Is Gemma 4 26B A4B IT or GPT-5.4 nano better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 39.0 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 nano does, with 400K tokens against 262K.
How many benchmarks do Gemma 4 26B A4B IT and GPT-5.4 nano share?
26 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and GPT-5.4 nano has 40.