Model comparison
Mistral Medium vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 36.3 on the Noometry Index.
Last verified . 25 shared benchmarks.
Mistral AI
NVIDIASummary
- They share 25 benchmarks with published results for both. Mistral Medium scores higher in 1 category and Nemotron 3 Ultra in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 86.7% for Nemotron 3 Ultra.
- Nemotron 3 Ultra is cheaper at $0.50 / $2.20 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
Side by side
| Mistral Medium | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 36.3 | 42.5 |
| Released | 2023-12-11 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 128K |
| Input $ / M tokens | $1.50 | $0.50 |
| Output $ / M tokens | $7.50 | $2.20 |
| Results tracked | 36 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Mistral Medium: 34.2 (#243), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Mistral Medium | Nemotron 3 Ultra |
|---|---|---|
| FrontierCode | 8% | 13.6% |
| SciCode | 40.2% | 40.3% |
| WeirdML | 43.7% | 43.5% |
| LMArena Coding | 1434 | 1468 |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Mistral Medium leads
Mistral Medium: 28.3 (#90), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Mistral Medium | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
| Berkeley Function Calling Leaderboard | 37.7% | — |
Reasoning Nemotron 3 Ultra leads
Mistral Medium: 24.0 (#167), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Mistral Medium | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 0% | 3.1% |
| LMArena Hard Prompts | 1426 | 1452 |
| DTBench | 75.5% | 90.1% |
| LMCA | 26.1% | 36.9% |
| Kagi LLM Benchmark | 50% | — |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 146.17 |
Math Nemotron 3 Ultra leads
Mistral Medium: 28.1 (#245), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Mistral Medium | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 86.7% |
| ProofBench | 9% | 2% |
| LMArena Math | 1408 | 1457 |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Nemotron 3 Ultra leads
Mistral Medium: 25.0 (#265), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Mistral Medium | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 59.5% | 85.4% |
| LMArena Expert | 1408 | 1472 |
| Humanity's Last Exam | 4.5% | — |
| Vectara Hallucination Rate | 22.7% | — |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), Nemotron 3 Ultra: —
| Benchmark | Mistral Medium | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Nemotron 3 Ultra leads
Mistral Medium: 52.1 (#91), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Mistral Medium | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1408 | 1427 |
| LMArena Chinese | 1447 | 1497 |
| LMArena French | 1459 | 1472 |
| LMArena German | 1432 | 1471 |
| LMArena Korean | 1380 | 1386 |
| LMArena Russian | 1411 | 1417 |
| LMArena Spanish | 1433 | 1454 |
| LMArena Japanese | 1378 | — |
Instruction Following Too close to call
Mistral Medium: 73.7 (#116), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Mistral Medium | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1398 | 1418 |
Long Context Nemotron 3 Ultra leads
Mistral Medium: 42.9 (#114), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Mistral Medium | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1406 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
Mistral Medium: 60.0 (#103), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Mistral Medium | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1424 | 1445 |
| LMArena Creative Writing | 1391 | 1398 |
| LMArena Multi-Turn | 1418 | 1411 |
| Short-Story Creative Writing | 77.3% | — |
| EQ-Bench Creative Writing | — | 1692 |
Frequently asked questions
Is Mistral Medium better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 36.3 on the Noometry Index.
Which is cheaper, Mistral Medium or Nemotron 3 Ultra?
Nemotron 3 Ultra is cheaper. It lists at $0.50 per million input tokens and $2.20 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Nemotron 3 Ultra better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 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 Ultra share?
25 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Nemotron 3 Ultra has 30.