Model comparison
Pixtral Large vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 32.2 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AI
StepFunSummary
- They share 1 benchmark with published results for both. Pixtral Large scores higher in 0 categories and Step 3 in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 32.9.
Side by side
| Pixtral Large | Step 3 | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 32.2 | 40.5 |
| Released | 2024-11-01 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 3 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Pixtral Large: —, Step 3: 40.1 (#147)
| Benchmark | Pixtral Large | Step 3 |
|---|---|---|
| LMArena Coding | — | 1367 |
Reasoning Step 3 leads
Pixtral Large: 21.7 (#218), Step 3: 28.4 (#105)
| Benchmark | Pixtral Large | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| EnigmaEval | 0.8% | — |
| LMArena Hard Prompts | — | 1355 |
Math Not comparable
Pixtral Large: —, Step 3: 37.6 (#148)
| Benchmark | Pixtral Large | Step 3 |
|---|---|---|
| LMArena Math | — | 1366 |
Knowledge Not comparable
Pixtral Large: —, Step 3: 36.8 (#164)
| Benchmark | Pixtral Large | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |
Multimodal Step 3 leads
Pixtral Large: 30.6 (#111), Step 3: 35.5 (#86)
| Benchmark | Pixtral Large | Step 3 |
|---|---|---|
| LMArena Vision | 1089 | 1177 |
Multilingual Not comparable
Pixtral Large: —, Step 3: 46.3 (#159)
| Benchmark | Pixtral Large | 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
Pixtral Large: —, Step 3: 70.4 (#164)
| Benchmark | Pixtral Large | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |
Long Context Not comparable
Pixtral Large: —, Step 3: 40.3 (#157)
| Benchmark | Pixtral Large | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Step 3 leads
Pixtral Large: 32.9 (#278), Step 3: 54.3 (#151)
| Benchmark | Pixtral Large | Step 3 |
|---|---|---|
| LMArena Text | — | 1350 |
| LMArena Creative Writing | — | 1321 |
| EQ-Bench Creative Writing | 988 | — |
| LMArena Multi-Turn | — | 1341 |
Frequently asked questions
Is Pixtral Large better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 32.2 on the Noometry Index.
How many benchmarks do Pixtral Large and Step 3 share?
1 benchmark has published results for both models. Pixtral Large has 3 scored results on Noometry and Step 3 has 17.