Model comparison
Mistral Medium vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 36.3 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AI
NVIDIASummary
- They share 19 benchmarks with published results for both. Mistral Medium scores higher in 5 categories and Nemotron 3 Super in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Super leads 38.9 to 25.0.
- The biggest single-benchmark swing is WeirdML: 43.7% for Mistral Medium and 38% for Nemotron 3 Super.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
Side by side
| Mistral Medium | Nemotron 3 Super | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 36.3 | 40.1 |
| Released | 2023-12-11 | 2026-03-11 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 131K |
| Input $ / M tokens | $1.50 | $0.08 |
| Output $ / M tokens | $7.50 | $0.45 |
| Results tracked | 36 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Mistral Medium: 34.2 (#243), Nemotron 3 Super: 39.4 (#158)
| Benchmark | Mistral Medium | Nemotron 3 Super |
|---|---|---|
| SciCode | 40.2% | 36% |
| WeirdML | 43.7% | 38% |
| LMArena Coding | 1434 | 1403 |
| ALE-Bench | 763.98 | 213.9 |
| FrontierCode | 8% | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.3 (#90), Nemotron 3 Super: —
| Benchmark | Mistral Medium | Nemotron 3 Super |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
Reasoning Mistral Medium leads
Mistral Medium: 24.0 (#167), Nemotron 3 Super: 18.7 (#276)
| Benchmark | Mistral Medium | Nemotron 3 Super |
|---|---|---|
| CritPt | 0% | 3.1% |
| LMArena Hard Prompts | 1426 | 1386 |
| Kagi LLM Benchmark | 50% | — |
| NYT Connections (extended) | — | 15.4% |
| DTBench | 75.5% | — |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |
Math Nemotron 3 Super leads
Mistral Medium: 28.1 (#245), Nemotron 3 Super: 39.6 (#101)
| Benchmark | Mistral Medium | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1408 | 1380 |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 32.2% | — |
| ProofBench | 9% | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Nemotron 3 Super leads
Mistral Medium: 25.0 (#265), Nemotron 3 Super: 38.9 (#139)
| Benchmark | Mistral Medium | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1408 | 1398 |
| GPQA Diamond | 59.5% | — |
| Humanity's Last Exam | 4.5% | — |
| Vectara Hallucination Rate | 22.7% | — |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), Nemotron 3 Super: —
| Benchmark | Mistral Medium | Nemotron 3 Super |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Mistral Medium leads
Mistral Medium: 52.1 (#91), Nemotron 3 Super: 48.4 (#144)
| Benchmark | Mistral Medium | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1408 | 1355 |
| LMArena Chinese | 1447 | 1432 |
| LMArena French | 1459 | 1405 |
| LMArena German | 1432 | 1341 |
| LMArena Russian | 1411 | 1336 |
| LMArena Spanish | 1433 | 1417 |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1380 | — |
Instruction Following Mistral Medium leads
Mistral Medium: 73.7 (#116), Nemotron 3 Super: 71.2 (#154)
| Benchmark | Mistral Medium | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1398 | 1347 |
Long Context Mistral Medium leads
Mistral Medium: 42.9 (#114), Nemotron 3 Super: 41.5 (#139)
| Benchmark | Mistral Medium | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1406 | 1362 |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), Nemotron 3 Super: 55.9 (#140)
| Benchmark | Mistral Medium | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1424 | 1378 |
| LMArena Creative Writing | 1391 | 1317 |
| LMArena Multi-Turn | 1418 | 1369 |
| Short-Story Creative Writing | 77.3% | — |
Frequently asked questions
Is Mistral Medium better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 36.3 on the Noometry Index.
Which is cheaper, Mistral Medium or Nemotron 3 Super?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Mistral Medium and Nemotron 3 Super share?
19 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Nemotron 3 Super has 21.