Model comparison
Claude 2.1 vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 25.2 on the Noometry Index.
Last verified . 0 shared benchmarks.
StepFunSummary
- The widest gap is in math, where Step 3 leads 37.6 to 10.2.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Claude 2.1 | Step 3 | |
|---|---|---|
| Provider | Anthropic | StepFun |
| Noometry Index | 25.2 | 40.5 |
| Released | 2023-11-21 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Claude 2.1: 26.2 (#327), Step 3: 40.1 (#147)
| Benchmark | Claude 2.1 | Step 3 |
|---|---|---|
| WeirdML | 7.1% | — |
| LMArena Coding | — | 1367 |
Reasoning Step 3 leads
Claude 2.1: 21.4 (#221), Step 3: 28.4 (#105)
| Benchmark | Claude 2.1 | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| LMArena Hard Prompts | — | 1355 |
| DTBench | 51% | — |
| Epoch Capabilities Index | 119.27 | — |
| ForecastBench | 54.2 | — |
Math Step 3 leads
Claude 2.1: 10.2 (#315), Step 3: 37.6 (#148)
| Benchmark | Claude 2.1 | Step 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| LMArena Math | — | 1366 |
Knowledge Step 3 leads
Claude 2.1: 15.4 (#292), Step 3: 36.8 (#164)
| Benchmark | Claude 2.1 | Step 3 |
|---|---|---|
| GPQA Diamond | 33% | — |
| LMArena Expert | — | 1333 |
| MMLU | 73.5% | — |
Multimodal Not comparable
Claude 2.1: —, Step 3: 35.5 (#86)
| Benchmark | Claude 2.1 | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Not comparable
Claude 2.1: —, Step 3: 46.3 (#159)
| Benchmark | Claude 2.1 | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1397 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1371 |
Instruction Following Not comparable
Claude 2.1: —, Step 3: 70.4 (#164)
| Benchmark | Claude 2.1 | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |
Long Context Not comparable
Claude 2.1: —, Step 3: 40.3 (#157)
| Benchmark | Claude 2.1 | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Not comparable
Claude 2.1: —, Step 3: 54.3 (#151)
| Benchmark | Claude 2.1 | Step 3 |
|---|---|---|
| LMArena Text | — | 1350 |
| LMArena Creative Writing | — | 1321 |
| LMArena Multi-Turn | — | 1341 |
Frequently asked questions
Is Claude 2.1 better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 25.2 on the Noometry Index.
Is Claude 2.1 or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 26.2 in the Noometry coding category.
How many benchmarks do Claude 2.1 and Step 3 share?
0 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and Step 3 has 17.