Model comparison
Llama 3-8B vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 25.5 on the Noometry Index.
Last verified . 15 shared benchmarks.
Meta
StepFunSummary
- They share 15 benchmarks with published results for both. Llama 3-8B scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 3 leads 36.8 to 7.8.
Side by side
| Llama 3-8B | Step 3 | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 25.5 | 40.5 |
| Released | 2024-04-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 34 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Llama 3-8B: 31.0 (#289), Step 3: 40.1 (#147)
| Benchmark | Llama 3-8B | Step 3 |
|---|---|---|
| LMArena Coding | 1152 | 1367 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Step 3 leads
Llama 3-8B: 14.3 (#326), Step 3: 28.4 (#105)
| Benchmark | Llama 3-8B | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.45 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Step 3 leads
Llama 3-8B: 8.8 (#323), Step 3: 37.6 (#148)
| Benchmark | Llama 3-8B | Step 3 |
|---|---|---|
| LMArena Math | 1151 | 1366 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
Knowledge Step 3 leads
Llama 3-8B: 7.8 (#308), Step 3: 36.8 (#164)
| Benchmark | Llama 3-8B | Step 3 |
|---|---|---|
| LMArena Expert | 1113 | 1333 |
| GPQA Diamond | 26.1% | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multimodal Not comparable
Llama 3-8B: —, Step 3: 35.5 (#86)
| Benchmark | Llama 3-8B | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Llama 3-8B: 30.8 (#261), Step 3: 46.3 (#159)
| Benchmark | Llama 3-8B | Step 3 |
|---|---|---|
| LMArena Non-English | 1098 | 1327 |
| LMArena Chinese | 1076 | 1397 |
| LMArena German | 1104 | 1371 |
| LMArena Korean | 1004 | 1269 |
| LMArena Russian | 1109 | 1331 |
| LMArena Spanish | 1173 | 1371 |
| LMArena French | 1159 | — |
| LMArena Japanese | 967 | — |
Instruction Following Step 3 leads
Llama 3-8B: 58.4 (#260), Step 3: 70.4 (#164)
| Benchmark | Llama 3-8B | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1127 | 1332 |
Long Context Step 3 leads
Llama 3-8B: 34.2 (#251), Step 3: 40.3 (#157)
| Benchmark | Llama 3-8B | Step 3 |
|---|---|---|
| LMArena Longer Query | 1128 | 1326 |
Writing & Preference Step 3 leads
Llama 3-8B: 37.5 (#256), Step 3: 54.3 (#151)
| Benchmark | Llama 3-8B | Step 3 |
|---|---|---|
| LMArena Text | 1166 | 1350 |
| LMArena Creative Writing | 1150 | 1321 |
| LMArena Multi-Turn | 1152 | 1341 |
Frequently asked questions
Is Llama 3-8B better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 25.5 on the Noometry Index.
Is Llama 3-8B or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Step 3 share?
15 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Step 3 has 17.