Model comparison
Mistral Nemo vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 26.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
StepFunSummary
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 28.5.
Side by side
| Mistral Nemo | Step 3 | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 26.4 | 40.5 |
| Released | 2024-07-01 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 10 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Nemo: —, Step 3: 40.1 (#147)
| Benchmark | Mistral Nemo | Step 3 |
|---|---|---|
| LMArena Coding | — | 1367 |
Agentic & Tool Use Not comparable
Mistral Nemo: 23.5 (#125), Step 3: —
| Benchmark | Mistral Nemo | Step 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.6% | — |
| BALROG | 17.6% | — |
Reasoning Step 3 leads
Mistral Nemo: 20.7 (#232), Step 3: 28.4 (#105)
| Benchmark | Mistral Nemo | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| LMArena Hard Prompts | — | 1355 |
| DTBench | 48.6% | — |
| Epoch Capabilities Index | 118.68 | — |
| PIQA | 83.5% | — |
Math Step 3 leads
Mistral Nemo: 25.5 (#268), Step 3: 37.6 (#148)
| Benchmark | Mistral Nemo | Step 3 |
|---|---|---|
| LMArena Math | — | 1366 |
| MATH Level 5 | 10.8% | — |
| GSM8K | 84.2% | — |
Knowledge Step 3 leads
Mistral Nemo: 12.3 (#298), Step 3: 36.8 (#164)
| Benchmark | Mistral Nemo | Step 3 |
|---|---|---|
| GPQA Diamond | 29.9% | — |
| LMArena Expert | — | 1333 |
| BoolQ | 82.5% | — |
Multimodal Not comparable
Mistral Nemo: —, Step 3: 35.5 (#86)
| Benchmark | Mistral Nemo | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Not comparable
Mistral Nemo: —, Step 3: 46.3 (#159)
| Benchmark | Mistral Nemo | 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
Mistral Nemo: —, Step 3: 70.4 (#164)
| Benchmark | Mistral Nemo | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |
Long Context Not comparable
Mistral Nemo: —, Step 3: 40.3 (#157)
| Benchmark | Mistral Nemo | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Step 3 leads
Mistral Nemo: 28.5 (#296), Step 3: 54.3 (#151)
| Benchmark | Mistral Nemo | Step 3 |
|---|---|---|
| LMArena Text | — | 1350 |
| LMArena Creative Writing | — | 1321 |
| EQ-Bench Creative Writing | 881 | — |
| LMArena Multi-Turn | — | 1341 |
Frequently asked questions
Is Mistral Nemo better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 26.4 on the Noometry Index.
How many benchmarks do Mistral Nemo and Step 3 share?
0 benchmarks have published results for both models. Mistral Nemo has 10 scored results on Noometry and Step 3 has 17.