Model comparison
Gemma 4 26B A4B IT vs Granite 3.1 8b Instruct
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 32.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
GoogleSummary
- They share 12 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 7 categories and Granite 3.1 8b Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 4 26B A4B IT leads 58.6 to 35.5.
Side by side
| Gemma 4 26B A4B IT | Granite 3.1 8b Instruct | |
|---|---|---|
| Provider | IBM | |
| Noometry Index | 43.5 | 32.4 |
| Released | 2026-04-02 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.09 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 28 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 39.0 (#164), Granite 3.1 8b Instruct: 34.5 (#233)
| Benchmark | Gemma 4 26B A4B IT | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Coding | 1447 | 1186 |
| LMArena WebDev | 1359 | — |
| SciCode | 40% | — |
| WeirdML | 35.2% | — |
| ALE-Bench | 927.17 | — |
Agentic & Tool Use Not comparable
Gemma 4 26B A4B IT: —, Granite 3.1 8b Instruct: 24.1 (#120)
| Benchmark | Gemma 4 26B A4B IT | Granite 3.1 8b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
Reasoning Too close to call
Gemma 4 26B A4B IT: 21.8 (#213), Granite 3.1 8b Instruct: 22.1 (#207)
| Benchmark | Gemma 4 26B A4B IT | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1439 | 1145 |
| CritPt | 0% | — |
| Chess Puzzles | 6% | — |
| DTBench | 74.9% | — |
| LMCA | 29.7% | — |
| Epoch Capabilities Index | 141.85 | — |
Math Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 47.6 (#67), Granite 3.1 8b Instruct: 33.0 (#209)
| Benchmark | Gemma 4 26B A4B IT | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Math | 1470 | 1152 |
| OTIS Mock AIME 2024-2025 | 82.2% | — |
Knowledge Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 45.7 (#85), Granite 3.1 8b Instruct: 31.1 (#220)
| Benchmark | Gemma 4 26B A4B IT | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Expert | 1447 | 1142 |
| GPQA Diamond | 73.2% | — |
| Vectara Hallucination Rate | 5.2% | — |
Multimodal Not comparable
Gemma 4 26B A4B IT: 40.6 (#46), Granite 3.1 8b Instruct: —
| Benchmark | Gemma 4 26B A4B IT | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Vision | 1260 | — |
Multilingual Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 53.1 (#71), Granite 3.1 8b Instruct: 30.9 (#260)
| Benchmark | Gemma 4 26B A4B IT | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Non-English | 1421 | 1099 |
| LMArena Chinese | 1495 | 1145 |
| LMArena Russian | 1434 | 1092 |
| LMArena French | 1460 | — |
| LMArena Spanish | 1417 | — |
Instruction Following Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 74.8 (#82), Granite 3.1 8b Instruct: 58.6 (#259)
| Benchmark | Gemma 4 26B A4B IT | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Instruction Following | 1420 | 1131 |
Long Context Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 43.6 (#91), Granite 3.1 8b Instruct: 35.2 (#241)
| Benchmark | Gemma 4 26B A4B IT | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Longer Query | 1428 | 1162 |
Writing & Preference Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 58.6 (#115), Granite 3.1 8b Instruct: 35.5 (#266)
| Benchmark | Gemma 4 26B A4B IT | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Text | 1434 | 1150 |
| LMArena Creative Writing | 1402 | 1129 |
| LMArena Multi-Turn | 1441 | 1108 |
| EQ-Bench Creative Writing | 1305 | — |
Frequently asked questions
Is Gemma 4 26B A4B IT better than Granite 3.1 8b Instruct?
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 32.4 on the Noometry Index.
Is Gemma 4 26B A4B IT or Granite 3.1 8b Instruct better for coding?
Gemma 4 26B A4B IT scores higher on coding benchmarks: 39.0 versus 34.5 in the Noometry coding category.
How many benchmarks do Gemma 4 26B A4B IT and Granite 3.1 8b Instruct share?
12 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and Granite 3.1 8b Instruct has 13.