Model comparison
Mercury 2.5 vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 33.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
StepFunSummary
- The widest gap is in math, where Step 3 leads 37.6 to 23.3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Mercury 2.5 | Step 3 | |
|---|---|---|
| Provider | Inception | StepFun |
| Noometry Index | 33.5 | 40.5 |
| Released | 2026-09-08 | — |
| Weights | Proprietary | Open |
| Context window | 260K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 4 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mercury 2.5: 39.5 (#156), Step 3: 40.1 (#147)
| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| SciCode | 38.5% | — |
| LMArena Coding | — | 1367 |
| ALE-Bench | 301.65 | — |
Reasoning Step 3 leads
Mercury 2.5: 22.4 (#193), Step 3: 28.4 (#105)
| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1355 |
Math Step 3 leads
Mercury 2.5: 23.3 (#272), Step 3: 37.6 (#148)
| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| ProofBench | 3% | — |
| LMArena Math | — | 1366 |
Knowledge Not comparable
Mercury 2.5: —, Step 3: 36.8 (#164)
| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |
Multimodal Not comparable
Mercury 2.5: —, Step 3: 35.5 (#86)
| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Not comparable
Mercury 2.5: —, Step 3: 46.3 (#159)
| Benchmark | Mercury 2.5 | 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
Mercury 2.5: —, Step 3: 70.4 (#164)
| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |
Long Context Not comparable
Mercury 2.5: —, Step 3: 40.3 (#157)
| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Not comparable
Mercury 2.5: —, Step 3: 54.3 (#151)
| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| LMArena Text | — | 1350 |
| LMArena Creative Writing | — | 1321 |
| LMArena Multi-Turn | — | 1341 |
Frequently asked questions
Is Mercury 2.5 better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 33.5 on the Noometry Index.
Is Mercury 2.5 or Step 3 better for coding?
They score almost the same on coding (39.5 vs 40.1); test both on your own repository before choosing.
How many benchmarks do Mercury 2.5 and Step 3 share?
0 benchmarks have published results for both models. Mercury 2.5 has 4 scored results on Noometry and Step 3 has 17.