Model comparison
Llama 3.1-8B vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 23.0 on the Noometry Index. Llama 3.1-8B costs 2.6× less per token, which makes it the better buy when Step 3.5 Flash's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Meta
StepFunSummary
- They share 17 benchmarks with published results for both. Llama 3.1-8B 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 10.2.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.10 / $0.30 for Step 3.5 Flash.
- Step 3.5 Flash accepts more context: 256K tokens versus 128K.
Side by side
| Llama 3.1-8B | Step 3.5 Flash | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 23.0 | 42.3 |
| Released | 2024-07-23 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 128K | 256K |
| Max output | 4K | 256K |
| Input $ / M tokens | $0.05 | $0.10 |
| Output $ / M tokens | $0.08 | $0.30 |
| Results tracked | 43 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Llama 3.1-8B: 20.2 (#340), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Llama 3.1-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1195 | 1436 |
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
| BigCodeBench Instruct | 32.8% | — |
| BigCodeBench Complete | 40.5% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Not comparable
Llama 3.1-8B: 22.5 (#131), Step 3.5 Flash: —
| Benchmark | Llama 3.1-8B | Step 3.5 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| BALROG | 15.1% | — |
Reasoning Step 3.5 Flash leads
Llama 3.1-8B: 14.9 (#321), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Llama 3.1-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1175 | 1411 |
| NYT Connections (extended) | — | 28.4% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 5.4% | — |
| Epoch Capabilities Index | 116.57 | — |
| PIQA | 81.2% | — |
Math Step 3.5 Flash leads
Llama 3.1-8B: 10.2 (#317), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Llama 3.1-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1179 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 1.7% | — |
| Omni-MATH | 13.7% | — |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |
Knowledge Step 3.5 Flash leads
Llama 3.1-8B: 8.0 (#307), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Llama 3.1-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1144 | 1421 |
| GPQA Diamond | 27% | — |
| MMLU-Pro | 40.6% | — |
| GPQA (HELM) | 24.7% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multilingual Step 3.5 Flash leads
Llama 3.1-8B: 34.0 (#249), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Llama 3.1-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1148 | 1385 |
| LMArena Chinese | 1151 | 1447 |
| LMArena French | 1177 | 1421 |
| LMArena German | 1144 | 1405 |
| LMArena Japanese | 1061 | 1354 |
| LMArena Korean | 1053 | 1352 |
| LMArena Russian | 1158 | 1385 |
| LMArena Spanish | 1169 | 1419 |
Instruction Following Step 3.5 Flash leads
Llama 3.1-8B: 58.9 (#258), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Llama 3.1-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1159 | 1385 |
| IFEval | 74.3% | — |
Long Context Step 3.5 Flash leads
Llama 3.1-8B: 35.8 (#238), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Llama 3.1-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1182 | 1402 |
Writing & Preference Step 3.5 Flash leads
Llama 3.1-8B: 29.7 (#290), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Llama 3.1-8B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1187 | 1403 |
| LMArena Creative Writing | 1154 | 1357 |
| LMArena Multi-Turn | 1172 | 1405 |
| EQ-Bench Creative Writing | 713 | — |
| WildBench | 68.7% | — |
Frequently asked questions
Is Llama 3.1-8B better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 23.0 on the Noometry Index. Llama 3.1-8B costs 2.6× less per token, which makes it the better buy when Step 3.5 Flash's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-8B or Step 3.5 Flash?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Step 3.5 Flash lists at $0.10 and $0.30.
Is Llama 3.1-8B or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Step 3.5 Flash does, with 256K tokens against 128K.
How many benchmarks do Llama 3.1-8B and Step 3.5 Flash share?
17 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Step 3.5 Flash has 19.