Model comparison
Mistral Large 3 vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 38.6 on the Noometry Index. Mistral Large 3 costs 2.8× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Mistral AI
NVIDIASummary
- They share 17 benchmarks with published results for both. Mistral Large 3 scores higher in 1 category and Nemotron 3 Ultra in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 35.5.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.60 / $2.40 for Nemotron 3 Ultra.
Side by side
| Mistral Large 3 | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 38.6 | 44.7 |
| Released | 2025-12-02 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 8K | 128K |
| Input $ / M tokens | $0.25 | $0.60 |
| Output $ / M tokens | $0.75 | $2.40 |
| Results tracked | 24 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Mistral Large 3: 34.1 (#230), Nemotron 3 Ultra: 37.7 (#174)
| Benchmark | Mistral Large 3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Coding | 1447 | 1468 |
| FrontierCode | — | 13.6% |
| LMArena WebDev | 1230 | — |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
Reasoning Nemotron 3 Ultra leads
Mistral Large 3: 14.6 (#314), Nemotron 3 Ultra: 30.3 (#78)
| Benchmark | Mistral Large 3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1429 | 1452 |
| Kagi LLM Benchmark | 50.9% | — |
| NYT Connections (extended) | 7.5% | — |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| Thematic Generalization | 23% | — |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.2 |
Math Mistral Large 3 leads
Mistral Large 3: 36.0 (#131), Nemotron 3 Ultra: 34.4 (#160)
| Benchmark | Mistral Large 3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Math | 1415 | 1456 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
Knowledge Nemotron 3 Ultra leads
Mistral Large 3: 35.5 (#173), Nemotron 3 Ultra: 52.5 (#56)
| Benchmark | Mistral Large 3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Expert | 1421 | 1472 |
| GPQA Diamond | — | 85.4% |
| Vectara Hallucination Rate | 14.5% | — |
Multimodal Not comparable
Mistral Large 3: 37.6 (#65), Nemotron 3 Ultra: —
| Benchmark | Mistral Large 3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1222 | — |
Multilingual Nemotron 3 Ultra leads
Mistral Large 3: 52.6 (#79), Nemotron 3 Ultra: 53.7 (#61)
| Benchmark | Mistral Large 3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1412 | 1427 |
| LMArena Chinese | 1448 | 1498 |
| LMArena French | 1456 | 1475 |
| LMArena German | 1438 | 1471 |
| LMArena Korean | 1384 | 1387 |
| LMArena Russian | 1412 | 1415 |
| LMArena Spanish | 1437 | 1452 |
| LMArena Japanese | 1399 | — |
Instruction Following Too close to call
Mistral Large 3: 74.1 (#104), Nemotron 3 Ultra: 74.9 (#84)
| Benchmark | Mistral Large 3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1402 | 1417 |
Long Context Too close to call
Mistral Large 3: 43.1 (#102), Nemotron 3 Ultra: 43.9 (#77)
| Benchmark | Mistral Large 3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1413 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
Mistral Large 3: 60.2 (#100), Nemotron 3 Ultra: 66.3 (#35)
| Benchmark | Mistral Large 3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1427 | 1444 |
| LMArena Creative Writing | 1385 | 1392 |
| EQ-Bench Creative Writing | 1412 | 1692 |
| LMArena Multi-Turn | 1429 | 1412 |
Frequently asked questions
Is Mistral Large 3 better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 38.6 on the Noometry Index. Mistral Large 3 costs 2.8× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Which is cheaper, Mistral Large 3 or Nemotron 3 Ultra?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Nemotron 3 Ultra lists at $0.60 and $2.40.
Is Mistral Large 3 or Nemotron 3 Ultra better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 37.7 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Mistral Large 3 and Nemotron 3 Ultra share?
17 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Nemotron 3 Ultra has 29.