# Mistral Large vs Nemotron 3 Ultra

> Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 31.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-large-vs-nemotron-3-ultra
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Mistral Large scores higher in 0 categories and Nemotron 3 Ultra in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Ultra leads 66.3 to 40.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Mistral Large and 86.7% for Nemotron 3 Ultra.
- Nemotron 3 Ultra is cheaper at $0.60 / $2.40 per million input/output tokens, against $2 / $6 for Mistral Large.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 131K.

## Snapshot

| | Mistral Large | Nemotron 3 Ultra |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 31.6 | 44.7 |
| Rank | 258 | 71 |
| Context | 131K | 262K |
| Input $/M | $2 | $0.60 |
| Output $/M | $6 | $2.40 |
| Weights | Open | Open |

## Coding

- Mistral Large: 33.8 (#240)
- Nemotron 3 Ultra: 37.7 (#174)

| Benchmark | Mistral Large | Nemotron 3 Ultra |
|---|---|---|
| SciCode | 36.2% | 40.3% |
| LMArena Coding | 1277 | 1468 |
| FrontierCode | — | 13.6% |
| WeirdML | — | 43.5% |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |

## Agentic & Tool Use

- Mistral Large: 28.4 (#83)
- Nemotron 3 Ultra: —

| Benchmark | Mistral Large | Nemotron 3 Ultra |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |

## Reasoning

- Mistral Large: 15.4 (#305)
- Nemotron 3 Ultra: 30.3 (#78)

| Benchmark | Mistral Large | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 0% | 3.1% |
| LMArena Hard Prompts | 1257 | 1452 |
| DTBench | 65.1% | 90.1% |
| LMCA | 16.7% | 36.9% |
| Epoch Capabilities Index | 128.52 | 146.2 |
| SimpleBench | 22.5% | — |
| Chess Puzzles | — | 12% |
| LiveBench Reasoning | 43.5% | — |
| Mystery Game Puzzles | — | 20% |
| LiveBench Data Analysis | 50.1% | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |

## Math

- Mistral Large: 17.1 (#285)
- Nemotron 3 Ultra: 34.4 (#160)

| Benchmark | Mistral Large | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 86.7% |
| LMArena Math | 1262 | 1456 |
| ProofBench | — | 2% |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |

## Knowledge

- Mistral Large: 30.0 (#224)
- Nemotron 3 Ultra: 52.5 (#56)

| Benchmark | Mistral Large | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 51.3% | 85.4% |
| LMArena Expert | 1232 | 1472 |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |

## Multilingual

- Mistral Large: 40.1 (#214)
- Nemotron 3 Ultra: 53.7 (#61)

| Benchmark | Mistral Large | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1237 | 1427 |
| LMArena Chinese | 1240 | 1498 |
| LMArena French | 1324 | 1475 |
| LMArena German | 1254 | 1471 |
| LMArena Korean | 1202 | 1387 |
| LMArena Russian | 1257 | 1415 |
| LMArena Spanish | 1268 | 1452 |
| LMArena Japanese | 1187 | — |

## Instruction Following

- Mistral Large: 68.1 (#186)
- Nemotron 3 Ultra: 74.9 (#84)

| Benchmark | Mistral Large | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1249 | 1417 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |

## Long Context

- Mistral Large: 38.3 (#194)
- Nemotron 3 Ultra: 43.9 (#77)

| Benchmark | Mistral Large | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1262 | 1437 |

## Writing & Preference

- Mistral Large: 40.9 (#237)
- Nemotron 3 Ultra: 66.3 (#35)

| Benchmark | Mistral Large | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1266 | 1444 |
| LMArena Creative Writing | 1243 | 1392 |
| EQ-Bench Creative Writing | 985 | 1692 |
| LMArena Multi-Turn | 1260 | 1412 |
| Short-Story Creative Writing | 69% | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |

## FAQ

### Is Mistral Large better than Nemotron 3 Ultra?

Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 31.6 on the Noometry Index.

### Which is cheaper, Mistral Large or Nemotron 3 Ultra?

Nemotron 3 Ultra is cheaper. It lists at $0.60 per million input tokens and $2.40 per million output tokens; Mistral Large lists at $2 and $6.

### Is Mistral Large or Nemotron 3 Ultra better for coding?

Nemotron 3 Ultra scores higher on coding benchmarks: 37.7 versus 33.8 in the Noometry coding category.

### Which has the bigger context window?

Nemotron 3 Ultra does, with 262K tokens against 131K.

### How many benchmarks do Mistral Large and Nemotron 3 Ultra share?

24 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Nemotron 3 Ultra has 29.