Model comparison
Step 3.5 Flash vs Tulu 3 (Tülu 3) 70B
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 33.0 on the Noometry Index.
Last verified . 11 shared benchmarks.
StepFun
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Step 3.5 Flash scores higher in 7 categories and Tulu 3 (Tülu 3) 70B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3.5 Flash leads 42.6 to 14.2.
Side by side
| Step 3.5 Flash | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | StepFun | Allen Institute for AI (Ai2) |
| Noometry Index | 42.3 | 33.0 |
| Released | 2026-01-29 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 256K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 19 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Step 3.5 Flash: 42.4 (#105), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Step 3.5 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1436 | 1235 |
Reasoning Tulu 3 (Tülu 3) 70B leads
Step 3.5 Flash: 22.2 (#202), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Step 3.5 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1220 |
| NYT Connections (extended) | 28.4% | — |
Math Step 3.5 Flash leads
Step 3.5 Flash: 42.6 (#84), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Step 3.5 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1408 | 1242 |
| MathArena Final-Answer Competitions | 66.8% | — |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
Knowledge Step 3.5 Flash leads
Step 3.5 Flash: 39.6 (#132), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Step 3.5 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| LMArena Expert | 1421 | — |
Multilingual Step 3.5 Flash leads
Step 3.5 Flash: 50.5 (#119), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Step 3.5 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1385 | 1236 |
| LMArena Chinese | 1447 | 1249 |
| LMArena Russian | 1385 | 1246 |
| LMArena French | 1421 | — |
| LMArena German | 1405 | — |
| LMArena Japanese | 1354 | — |
| LMArena Korean | 1352 | — |
| LMArena Spanish | 1419 | — |
Instruction Following Step 3.5 Flash leads
Step 3.5 Flash: 73.1 (#124), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Step 3.5 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1385 | 1233 |
Long Context Step 3.5 Flash leads
Step 3.5 Flash: 42.8 (#117), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Step 3.5 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1402 | 1224 |
Writing & Preference Step 3.5 Flash leads
Step 3.5 Flash: 58.8 (#113), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Step 3.5 Flash | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1403 | 1256 |
| LMArena Creative Writing | 1357 | 1231 |
| LMArena Multi-Turn | 1405 | 1252 |
Frequently asked questions
Is Step 3.5 Flash better than Tulu 3 (Tülu 3) 70B?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 33.0 on the Noometry Index.
Is Step 3.5 Flash or Tulu 3 (Tülu 3) 70B better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 36.0 in the Noometry coding category.
How many benchmarks do Step 3.5 Flash and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. Step 3.5 Flash has 19 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.