Model comparison
Llama 3-8B vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 25.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
StepFunSummary
- They share 17 benchmarks with published results for both. Llama 3-8B 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 math, where Step 3.5 Flash leads 42.6 to 8.8.
Side by side
| Llama 3-8B | Step 3.5 Flash | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 25.5 | 42.3 |
| Released | 2024-04-18 | 2026-01-29 |
| Weights | Open | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 34 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Llama 3-8B: 31.0 (#289), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Llama 3-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1152 | 1436 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Step 3.5 Flash leads
Llama 3-8B: 14.3 (#326), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Llama 3-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1411 |
| NYT Connections (extended) | — | 28.4% |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.45 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Step 3.5 Flash leads
Llama 3-8B: 8.8 (#323), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Llama 3-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1151 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
Knowledge Step 3.5 Flash leads
Llama 3-8B: 7.8 (#308), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Llama 3-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1113 | 1421 |
| GPQA Diamond | 26.1% | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Step 3.5 Flash leads
Llama 3-8B: 30.8 (#261), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Llama 3-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1098 | 1385 |
| LMArena Chinese | 1076 | 1447 |
| LMArena French | 1159 | 1421 |
| LMArena German | 1104 | 1405 |
| LMArena Japanese | 967 | 1354 |
| LMArena Korean | 1004 | 1352 |
| LMArena Russian | 1109 | 1385 |
| LMArena Spanish | 1173 | 1419 |
Instruction Following Step 3.5 Flash leads
Llama 3-8B: 58.4 (#260), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Llama 3-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1127 | 1385 |
Long Context Step 3.5 Flash leads
Llama 3-8B: 34.2 (#251), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Llama 3-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1128 | 1402 |
Writing & Preference Step 3.5 Flash leads
Llama 3-8B: 37.5 (#256), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Llama 3-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1166 | 1403 |
| LMArena Creative Writing | 1150 | 1357 |
| LMArena Multi-Turn | 1152 | 1405 |
Frequently asked questions
Is Llama 3-8B better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 25.5 on the Noometry Index.
Is Llama 3-8B or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Step 3.5 Flash share?
17 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Step 3.5 Flash has 19.