Model comparison
Mistral Large vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 31.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
StepFunSummary
- They share 12 benchmarks with published results for both. Mistral Large scores higher in 1 category and Step 2 16k Exp 202412 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 2 16k Exp 202412 leads 36.3 to 18.2.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Mistral Large | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 31.9 | 39.2 |
| Released | 2024-02-26 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 51 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Mistral Large: 34.3 (#240), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Mistral Large | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1277 | 1316 |
| SciCode | 36.2% | — |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.6 (#89), Step 2 16k Exp 202412: —
| Benchmark | Mistral Large | Step 2 16k Exp 202412 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Step 2 16k Exp 202412 leads
Mistral Large: 15.8 (#310), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Mistral Large | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1299 |
| SimpleBench | 22.5% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.5% | — |
| DTBench | 65.1% | — |
| LiveBench Data Analysis | 50.1% | — |
| LMCA | 16.7% | — |
| Epoch Capabilities Index | 128.52 | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Step 2 16k Exp 202412 leads
Mistral Large: 18.2 (#291), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Mistral Large | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1262 | 1304 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Step 2 16k Exp 202412 leads
Mistral Large: 30.1 (#230), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Mistral Large | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1232 | 1279 |
| GPQA Diamond | 51.3% | — |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multilingual Step 2 16k Exp 202412 leads
Mistral Large: 40.0 (#219), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Mistral Large | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1237 | 1290 |
| LMArena Chinese | 1240 | 1331 |
| LMArena Russian | 1257 | 1324 |
| LMArena French | 1325 | — |
| LMArena German | 1254 | — |
| LMArena Japanese | 1188 | — |
| LMArena Korean | 1202 | — |
| LMArena Spanish | 1268 | — |
Instruction Following Too close to call
Mistral Large: 67.9 (#191), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Mistral Large | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1249 | 1287 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Step 2 16k Exp 202412 leads
Mistral Large: 38.3 (#199), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Mistral Large | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1261 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Mistral Large: 40.7 (#242), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Mistral Large | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1266 | 1321 |
| LMArena Creative Writing | 1243 | 1328 |
| LMArena Multi-Turn | 1260 | 1292 |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 31.9 on the Noometry Index.
Is Mistral Large or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 38.5 versus 34.3 in the Noometry coding category.
How many benchmarks do Mistral Large and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Step 2 16k Exp 202412 has 12.