Model comparison
Granite 3.0 8b Instruct vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 31.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
StepFunSummary
- They share 12 benchmarks with published results for both. Granite 3.0 8b Instruct scores higher in 0 categories and Step 3.5 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3.5 Flash leads 58.8 to 31.1.
Side by side
| Granite 3.0 8b Instruct | Step 3.5 Flash | |
|---|---|---|
| Provider | IBM | StepFun |
| Noometry Index | 31.6 | 42.3 |
| Released | — | 2026-01-29 |
| Weights | Open | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 14 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Granite 3.0 8b Instruct: 29.7 (#301), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Granite 3.0 8b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1112 | 1436 |
| BigCodeBench Instruct | 29.3% | — |
| BigCodeBench Complete | 35.4% | — |
Reasoning Step 3.5 Flash leads
Granite 3.0 8b Instruct: 20.9 (#230), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Granite 3.0 8b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1092 | 1411 |
| NYT Connections (extended) | — | 28.4% |
Math Step 3.5 Flash leads
Granite 3.0 8b Instruct: 32.8 (#210), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Granite 3.0 8b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1143 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
Knowledge Step 3.5 Flash leads
Granite 3.0 8b Instruct: 29.6 (#236), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Granite 3.0 8b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1087 | 1421 |
Multilingual Step 3.5 Flash leads
Granite 3.0 8b Instruct: 27.2 (#276), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Granite 3.0 8b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1037 | 1385 |
| LMArena Chinese | 1063 | 1447 |
| LMArena Russian | 1060 | 1385 |
| LMArena French | — | 1421 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1354 |
| LMArena Korean | — | 1352 |
| LMArena Spanish | — | 1419 |
Instruction Following Step 3.5 Flash leads
Granite 3.0 8b Instruct: 56.0 (#276), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Granite 3.0 8b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1088 | 1385 |
Long Context Step 3.5 Flash leads
Granite 3.0 8b Instruct: 34.0 (#252), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Granite 3.0 8b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1122 | 1402 |
Writing & Preference Step 3.5 Flash leads
Granite 3.0 8b Instruct: 31.1 (#285), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Granite 3.0 8b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1096 | 1403 |
| LMArena Creative Writing | 1071 | 1357 |
| LMArena Multi-Turn | 1063 | 1405 |
Frequently asked questions
Is Granite 3.0 8b Instruct better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 31.6 on the Noometry Index.
Is Granite 3.0 8b Instruct or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 29.7 in the Noometry coding category.
How many benchmarks do Granite 3.0 8b Instruct and Step 3.5 Flash share?
12 benchmarks have published results for both models. Granite 3.0 8b Instruct has 14 scored results on Noometry and Step 3.5 Flash has 19.