Model comparison
Granite 4.2 8B vs Step 3.7 Flash
Granite 4.2 8B is the stronger model overall, scoring 40.5 to 37.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
StepFunSummary
- The widest gap is in reasoning, where Granite 4.2 8B leads 26.6 to 21.6.
- Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.18 / $1.11 for Step 3.7 Flash.
- Step 3.7 Flash accepts more context: 256K tokens versus 131K.
Side by side
| Granite 4.2 8B | Step 3.7 Flash | |
|---|---|---|
| Provider | IBM | StepFun |
| Noometry Index | 40.5 | 37.3 |
| Released | — | 2026-05-29 |
| Weights | Open | Open |
| Context window | 131K | 256K |
| Max output | 118K | 256K |
| Input $ / M tokens | $0.06 | $0.18 |
| Output $ / M tokens | $0.25 | $1.11 |
| Results tracked | 11 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Granite 4.2 8B: 40.5 (#137), Step 3.7 Flash: 40.0 (#150)
| Benchmark | Granite 4.2 8B | Step 3.7 Flash |
|---|---|---|
| SciCode | — | 40% |
| LMArena Coding | 1380 | — |
| ALE-Bench | — | 694.12 |
Reasoning Granite 4.2 8B leads
Granite 4.2 8B: 26.6 (#131), Step 3.7 Flash: 21.6 (#219)
| Benchmark | Granite 4.2 8B | Step 3.7 Flash |
|---|---|---|
| NYT Connections (extended) | — | 39.7% |
| CritPt | — | 2.3% |
| LMArena Hard Prompts | 1329 | — |
Math Not comparable
Granite 4.2 8B: —, Step 3.7 Flash: 42.9 (#82)
| Benchmark | Granite 4.2 8B | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
Knowledge Not comparable
Granite 4.2 8B: 38.4 (#145), Step 3.7 Flash: —
| Benchmark | Granite 4.2 8B | Step 3.7 Flash |
|---|---|---|
| LMArena Expert | 1384 | — |
Multilingual Not comparable
Granite 4.2 8B: 44.5 (#178), Step 3.7 Flash: —
| Benchmark | Granite 4.2 8B | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1302 | — |
| LMArena Chinese | 1366 | — |
| LMArena Russian | 1285 | — |
Instruction Following Not comparable
Granite 4.2 8B: 68.7 (#184), Step 3.7 Flash: —
| Benchmark | Granite 4.2 8B | Step 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1301 | — |
Long Context Not comparable
Granite 4.2 8B: 40.3 (#159), Step 3.7 Flash: —
| Benchmark | Granite 4.2 8B | Step 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1324 | — |
Writing & Preference Not comparable
Granite 4.2 8B: 49.6 (#189), Step 3.7 Flash: —
| Benchmark | Granite 4.2 8B | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1320 | — |
| LMArena Creative Writing | 1236 | — |
| LMArena Multi-Turn | 1301 | — |
Frequently asked questions
Is Granite 4.2 8B better than Step 3.7 Flash?
Granite 4.2 8B is the stronger model overall, scoring 40.5 to 37.3 on the Noometry Index.
Which is cheaper, Granite 4.2 8B or Step 3.7 Flash?
Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; Step 3.7 Flash lists at $0.18 and $1.11.
Is Granite 4.2 8B or Step 3.7 Flash better for coding?
They score almost the same on coding (40.5 vs 40.0); test both on your own repository before choosing.
Which has the bigger context window?
Step 3.7 Flash does, with 256K tokens against 131K.
How many benchmarks do Granite 4.2 8B and Step 3.7 Flash share?
0 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and Step 3.7 Flash has 5.