Model comparison
Claude 3 Sonnet vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 38.6 to 28.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
StepFunSummary
- They share 12 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Step 2 16k Exp 202412 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 2 16k Exp 202412 leads 33.6 to 10.0.
Side by side
| Claude 3 Sonnet | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | Anthropic | StepFun |
| Noometry Index | 28.8 | 38.6 |
| Released | 2024-02-29 | — |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Claude 3 Sonnet: 29.2 (#296), Step 2 16k Exp 202412: 37.9 (#170)
| Benchmark | Claude 3 Sonnet | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1223 | 1316 |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Reasoning Step 2 16k Exp 202412 leads
Claude 3 Sonnet: 19.7 (#232), Step 2 16k Exp 202412: 24.8 (#140)
| Benchmark | Claude 3 Sonnet | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1299 |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.69 | — |
| WinoGrande | 75.1% | — |
Math Step 2 16k Exp 202412 leads
Claude 3 Sonnet: 10.0 (#305), Step 2 16k Exp 202412: 33.6 (#171)
| Benchmark | Claude 3 Sonnet | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1213 | 1305 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 18.2% | — |
Knowledge Step 2 16k Exp 202412 leads
Claude 3 Sonnet: 21.1 (#271), Step 2 16k Exp 202412: 34.6 (#187)
| Benchmark | Claude 3 Sonnet | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1173 | 1279 |
| GPQA Diamond | 40.6% | — |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 24.7 (#120), Step 2 16k Exp 202412: —
| Benchmark | Claude 3 Sonnet | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Step 2 16k Exp 202412 leads
Claude 3 Sonnet: 38.0 (#229), Step 2 16k Exp 202412: 43.9 (#176)
| Benchmark | Claude 3 Sonnet | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1205 | 1290 |
| LMArena Chinese | 1188 | 1331 |
| LMArena Russian | 1227 | 1324 |
| LMArena French | 1228 | — |
| LMArena German | 1204 | — |
| LMArena Japanese | 1131 | — |
| LMArena Korean | 1128 | — |
| LMArena Spanish | 1204 | — |
Instruction Following Step 2 16k Exp 202412 leads
Claude 3 Sonnet: 63.1 (#230), Step 2 16k Exp 202412: 68.1 (#187)
| Benchmark | Claude 3 Sonnet | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1200 | 1287 |
Long Context Step 2 16k Exp 202412 leads
Claude 3 Sonnet: 36.7 (#223), Step 2 16k Exp 202412: 39.7 (#165)
| Benchmark | Claude 3 Sonnet | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1211 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Claude 3 Sonnet: 42.3 (#233), Step 2 16k Exp 202412: 52.5 (#168)
| Benchmark | Claude 3 Sonnet | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1218 | 1321 |
| LMArena Creative Writing | 1186 | 1328 |
| LMArena Multi-Turn | 1227 | 1292 |
Frequently asked questions
Is Claude 3 Sonnet better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 38.6 to 28.8 on the Noometry Index.
Is Claude 3 Sonnet or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 37.9 versus 29.2 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Step 2 16k Exp 202412 has 12.