Model comparison
AI Co-Mathematician vs Step 5 Preview
Step 5 Preview has enough public results to be ranked (#58); AI Co-Mathematician does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Google
StepFunSummary
- The widest gap is in math, where AI Co-Mathematician leads 72.3 to 46.1.
Side by side
| AI Co-Mathematician | Step 5 Preview | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 58.1 | 47.9 |
| Released | 2026-05-08 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 2 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
AI Co-Mathematician: —, Step 5 Preview: 51.8 (#36)
| Benchmark | AI Co-Mathematician | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| LMArena Coding | — | 1480 |
Reasoning Not comparable
AI Co-Mathematician: —, Step 5 Preview: 40.0 (#57)
| Benchmark | AI Co-Mathematician | Step 5 Preview |
|---|---|---|
| CritPt | — | 20.9% |
| LMArena Hard Prompts | — | 1465 |
Math AI Co-Mathematician leads
AI Co-Mathematician: 72.3, Step 5 Preview: 46.1 (#72)
| Benchmark | AI Co-Mathematician | Step 5 Preview |
|---|---|---|
| FrontierMath Tier 4 | 75.6% | — |
| ProofBench | — | 42% |
| LMArena Math | — | 1470 |
| FrontierMath Tier 4 (v1) | 47.9% | — |
Knowledge Not comparable
AI Co-Mathematician: —, Step 5 Preview: 41.2 (#112)
| Benchmark | AI Co-Mathematician | Step 5 Preview |
|---|---|---|
| LMArena Expert | — | 1470 |
Multimodal Not comparable
AI Co-Mathematician: —, Step 5 Preview: 41.0 (#41)
| Benchmark | AI Co-Mathematician | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Not comparable
AI Co-Mathematician: —, Step 5 Preview: 53.8 (#54)
| Benchmark | AI Co-Mathematician | Step 5 Preview |
|---|---|---|
| LMArena Non-English | — | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Not comparable
AI Co-Mathematician: —, Step 5 Preview: 76.0 (#50)
| Benchmark | AI Co-Mathematician | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | — | 1444 |
Long Context Not comparable
AI Co-Mathematician: —, Step 5 Preview: 44.5 (#64)
| Benchmark | AI Co-Mathematician | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Not comparable
AI Co-Mathematician: —, Step 5 Preview: 62.8 (#71)
| Benchmark | AI Co-Mathematician | Step 5 Preview |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1410 |
| LMArena Multi-Turn | — | 1447 |
Frequently asked questions
Is AI Co-Mathematician better than Step 5 Preview?
Step 5 Preview has enough public results to be ranked (#58); AI Co-Mathematician does not yet, so treat this comparison as directional.
How many benchmarks do AI Co-Mathematician and Step 5 Preview share?
0 benchmarks have published results for both models. AI Co-Mathematician has 2 scored results on Noometry and Step 5 Preview has 18.