Model comparison
Step 3.7 Flash vs Tulu 3 (Tülu 3) 70B
Step 3.7 Flash is the stronger model overall, scoring 37.3 to 33.0 on the Noometry Index.
Last verified . 0 shared benchmarks.
StepFun
Allen Institute for AI (Ai2)Summary
- The widest gap is in math, where Step 3.7 Flash leads 42.9 to 14.2.
Side by side
| Step 3.7 Flash | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | StepFun | Allen Institute for AI (Ai2) |
| Noometry Index | 37.3 | 33.0 |
| Released | 2026-05-29 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 256K | — |
| Input $ / M tokens | $0.18 | — |
| Output $ / M tokens | $1.11 | — |
| Results tracked | 5 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.7 Flash leads
Step 3.7 Flash: 40.0 (#150), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Step 3.7 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| SciCode | 40% | — |
| LMArena Coding | — | 1235 |
| ALE-Bench | 694.12 | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Step 3.7 Flash: 21.6 (#219), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Step 3.7 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| NYT Connections (extended) | 39.7% | — |
| CritPt | 2.3% | — |
| LMArena Hard Prompts | — | 1220 |
Math Step 3.7 Flash leads
Step 3.7 Flash: 42.9 (#82), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Step 3.7 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| MathArena Final-Answer Competitions | 68.5% | — |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| LMArena Math | — | 1242 |
| MATH Level 5 | — | 42.7% |
Knowledge Not comparable
Step 3.7 Flash: —, Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Step 3.7 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
Multilingual Not comparable
Step 3.7 Flash: —, Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Step 3.7 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | — | 1236 |
| LMArena Chinese | — | 1249 |
| LMArena Russian | — | 1246 |
Instruction Following Not comparable
Step 3.7 Flash: —, Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Step 3.7 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | — | 1233 |
Long Context Not comparable
Step 3.7 Flash: —, Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Step 3.7 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | — | 1224 |
Writing & Preference Not comparable
Step 3.7 Flash: —, Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Step 3.7 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | — | 1256 |
| LMArena Creative Writing | — | 1231 |
| LMArena Multi-Turn | — | 1252 |
Frequently asked questions
Is Step 3.7 Flash better than Tulu 3 (Tülu 3) 70B?
Step 3.7 Flash is the stronger model overall, scoring 37.3 to 33.0 on the Noometry Index.
Is Step 3.7 Flash or Tulu 3 (Tülu 3) 70B better for coding?
Step 3.7 Flash scores higher on coding benchmarks: 40.0 versus 36.0 in the Noometry coding category.
How many benchmarks do Step 3.7 Flash and Tulu 3 (Tülu 3) 70B share?
0 benchmarks have published results for both models. Step 3.7 Flash has 5 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.