Model comparison
Llama2 70b Steerlm Chat vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 31.8 on the Noometry Index.
Last verified . 9 shared benchmarks.
NVIDIA
StepFunSummary
- They share 9 benchmarks with published results for both. Llama2 70b Steerlm Chat scores higher in 0 categories and Step 3.5 Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3.5 Flash leads 58.8 to 31.6.
Side by side
| Llama2 70b Steerlm Chat | Step 3.5 Flash | |
|---|---|---|
| Provider | NVIDIA | StepFun |
| Noometry Index | 31.8 | 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 | 9 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Llama2 70b Steerlm Chat: 29.9 (#300), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Llama2 70b Steerlm Chat | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1025 | 1436 |
Reasoning Step 3.5 Flash leads
Llama2 70b Steerlm Chat: 20.0 (#246), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Llama2 70b Steerlm Chat | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1047 | 1411 |
| NYT Connections (extended) | — | 28.4% |
Math Step 3.5 Flash leads
Llama2 70b Steerlm Chat: 31.3 (#226), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Llama2 70b Steerlm Chat | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1072 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
Knowledge Not comparable
Llama2 70b Steerlm Chat: —, Step 3.5 Flash: 39.6 (#132)
| Benchmark | Llama2 70b Steerlm Chat | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | — | 1421 |
Multilingual Step 3.5 Flash leads
Llama2 70b Steerlm Chat: 28.8 (#270), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Llama2 70b Steerlm Chat | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1063 | 1385 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1421 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1354 |
| LMArena Korean | — | 1352 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1419 |
Instruction Following Step 3.5 Flash leads
Llama2 70b Steerlm Chat: 54.2 (#279), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Llama2 70b Steerlm Chat | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1060 | 1385 |
Long Context Step 3.5 Flash leads
Llama2 70b Steerlm Chat: 30.4 (#288), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Llama2 70b Steerlm Chat | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 998 | 1402 |
Writing & Preference Step 3.5 Flash leads
Llama2 70b Steerlm Chat: 31.6 (#283), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Llama2 70b Steerlm Chat | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1098 | 1403 |
| LMArena Creative Writing | 1091 | 1357 |
| LMArena Multi-Turn | 1058 | 1405 |
Frequently asked questions
Is Llama2 70b Steerlm Chat better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 31.8 on the Noometry Index.
Is Llama2 70b Steerlm Chat or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 29.9 in the Noometry coding category.
How many benchmarks do Llama2 70b Steerlm Chat and Step 3.5 Flash share?
9 benchmarks have published results for both models. Llama2 70b Steerlm Chat has 9 scored results on Noometry and Step 3.5 Flash has 19.