Model comparison
Gemma 4 26B A4B IT vs Gemma 4 31B IT
Gemma 4 26B A4B IT and Gemma 4 31B IT score almost the same on the Noometry Index (43.1 vs 43.2), so choose on price, context window or the category you care about most.
Last verified . 28 shared benchmarks.
GoogleSummary
- They share 28 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 2 categories and Gemma 4 31B IT in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 4 26B A4B IT leads 45.6 to 37.9.
- The biggest single-benchmark swing is WeirdML: 35.2% for Gemma 4 26B A4B IT and 52.3% for Gemma 4 31B IT.
- Gemma 4 26B A4B IT is cheaper at $0.0765 / $0.26 per million input/output tokens, against $0.09 / $0.34 for Gemma 4 31B IT.
Side by side
| Gemma 4 26B A4B IT | Gemma 4 31B IT | |
|---|---|---|
| Provider | ||
| Noometry Index | 43.1 | 43.2 |
| Released | 2026-04-02 | 2026-04-02 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 33K | 33K |
| Input $ / M tokens | $0.0765 | $0.09 |
| Output $ / M tokens | $0.26 | $0.34 |
| Results tracked | 28 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemma 4 26B A4B IT: 38.8 (#156), Gemma 4 31B IT: 41.9 (#98)
| Benchmark | Gemma 4 26B A4B IT | Gemma 4 31B IT |
|---|---|---|
| LMArena WebDev | 1359 | 1364 |
| SciCode | 40% | 43.4% |
| WeirdML | 35.2% | 52.3% |
| LMArena Coding | 1446 | 1459 |
| ALE-Bench | 927.17 | 925.5 |
Reasoning Gemma 4 31B IT leads
Gemma 4 26B A4B IT: 21.1 (#205), Gemma 4 31B IT: 26.4 (#119)
| Benchmark | Gemma 4 26B A4B IT | Gemma 4 31B IT |
|---|---|---|
| CritPt | 0% | 1.4% |
| Chess Puzzles | 6% | 5% |
| LMArena Hard Prompts | 1438 | 1448 |
| DTBench | 74.9% | 82.7% |
| LMCA | 29.7% | 39.3% |
| Epoch Capabilities Index | 141.85 | 142.74 |
| Kagi LLM Benchmark | — | 63.5% |
| NYT Connections (extended) | — | 70.6% |
| Thematic Generalization | — | 53% |
| Surface Evolver Bench | — | 30.6% |
Math Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 45.7 (#61), Gemma 4 31B IT: 41.3 (#72)
| Benchmark | Gemma 4 26B A4B IT | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 82.2% | 73.3% |
| LMArena Math | 1469 | 1464 |
Knowledge Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 45.6 (#79), Gemma 4 31B IT: 37.9 (#141)
| Benchmark | Gemma 4 26B A4B IT | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 73.2% | 75.8% |
| Vectara Hallucination Rate | 5.2% | 7.4% |
| LMArena Expert | 1447 | 1465 |
| SimpleQA Verified | — | 10.4% |
Multimodal Gemma 4 31B IT leads
Gemma 4 26B A4B IT: 39.9 (#43), Gemma 4 31B IT: 41.0 (#32)
| Benchmark | Gemma 4 26B A4B IT | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | 1260 | 1278 |
| LMArena Document | — | 1425 |
Multilingual Too close to call
Gemma 4 26B A4B IT: 53.3 (#68), Gemma 4 31B IT: 54.0 (#52)
| Benchmark | Gemma 4 26B A4B IT | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1422 | 1431 |
| LMArena Chinese | 1495 | 1478 |
| LMArena French | 1459 | 1436 |
| LMArena Russian | 1434 | 1462 |
| LMArena Spanish | 1415 | 1443 |
Instruction Following Too close to call
Gemma 4 26B A4B IT: 75.0 (#78), Gemma 4 31B IT: 75.6 (#58)
| Benchmark | Gemma 4 26B A4B IT | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1420 | 1433 |
Long Context Too close to call
Gemma 4 26B A4B IT: 43.6 (#87), Gemma 4 31B IT: 44.2 (#67)
| Benchmark | Gemma 4 26B A4B IT | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1427 | 1446 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 26B A4B IT: 58.8 (#110), Gemma 4 31B IT: 60.7 (#92)
| Benchmark | Gemma 4 26B A4B IT | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1434 | 1443 |
| LMArena Creative Writing | 1401 | 1416 |
| EQ-Bench Creative Writing | 1305 | 1368 |
| LMArena Multi-Turn | 1442 | 1452 |
| EQ-Bench 4 | — | 1120 |
Frequently asked questions
Is Gemma 4 26B A4B IT better than Gemma 4 31B IT?
Gemma 4 26B A4B IT and Gemma 4 31B IT score almost the same on the Noometry Index (43.1 vs 43.2), so choose on price, context window or the category you care about most.
Which is cheaper, Gemma 4 26B A4B IT or Gemma 4 31B IT?
Gemma 4 26B A4B IT is cheaper. It lists at $0.0765 per million input tokens and $0.26 per million output tokens; Gemma 4 31B IT lists at $0.09 and $0.34.
Is Gemma 4 26B A4B IT or Gemma 4 31B IT better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 38.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Gemma 4 26B A4B IT and Gemma 4 31B IT share?
28 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and Gemma 4 31B IT has 35.