Model comparison
Llama 3.1 Tulu 3 8b vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 35.7 on the Noometry Index.
Last verified . 11 shared benchmarks.
Allen Institute for AI (Ai2)
StepFunSummary
- They share 11 benchmarks with published results for both. Llama 3.1 Tulu 3 8b scores higher in 0 categories and Step 2 16k Exp 202412 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 2 16k Exp 202412 leads 52.3 to 39.7.
- Llama 3.1 Tulu 3 8b has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1 Tulu 3 8b | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | StepFun |
| Noometry Index | 35.7 | 39.2 |
| Released | — | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Llama 3.1 Tulu 3 8b: 34.4 (#235), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Llama 3.1 Tulu 3 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1183 | 1316 |
Reasoning Step 2 16k Exp 202412 leads
Llama 3.1 Tulu 3 8b: 22.8 (#188), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Llama 3.1 Tulu 3 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1299 |
Math Step 2 16k Exp 202412 leads
Llama 3.1 Tulu 3 8b: 33.9 (#198), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Llama 3.1 Tulu 3 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1195 | 1304 |
Knowledge Not comparable
Llama 3.1 Tulu 3 8b: —, Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Llama 3.1 Tulu 3 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | — | 1279 |
Multilingual Step 2 16k Exp 202412 leads
Llama 3.1 Tulu 3 8b: 35.4 (#246), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Llama 3.1 Tulu 3 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1169 | 1290 |
| LMArena Chinese | 1176 | 1331 |
| LMArena Russian | 1193 | 1324 |
Instruction Following Step 2 16k Exp 202412 leads
Llama 3.1 Tulu 3 8b: 61.3 (#246), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Llama 3.1 Tulu 3 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1287 |
Long Context Step 2 16k Exp 202412 leads
Llama 3.1 Tulu 3 8b: 35.8 (#239), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Llama 3.1 Tulu 3 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1181 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Llama 3.1 Tulu 3 8b: 39.7 (#245), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Llama 3.1 Tulu 3 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1193 | 1321 |
| LMArena Creative Writing | 1182 | 1328 |
| LMArena Multi-Turn | 1154 | 1292 |
Frequently asked questions
Is Llama 3.1 Tulu 3 8b better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 35.7 on the Noometry Index.
Is Llama 3.1 Tulu 3 8b or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 38.5 versus 34.4 in the Noometry coding category.
How many benchmarks do Llama 3.1 Tulu 3 8b and Step 2 16k Exp 202412 share?
11 benchmarks have published results for both models. Llama 3.1 Tulu 3 8b has 11 scored results on Noometry and Step 2 16k Exp 202412 has 12.