Model comparison
Mistral Large vs Nemotron 3.5 Lightning
Nemotron 3.5 Lightning is the stronger model overall, scoring 40.0 to 31.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AI
NVIDIASummary
- They share 18 benchmarks with published results for both. Mistral Large scores higher in 0 categories and Nemotron 3.5 Lightning in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Nemotron 3.5 Lightning leads 37.5 to 18.2.
- Nemotron 3.5 Lightning is cheaper at $0.05 / $0.20 per million input/output tokens, against $2 / $6 for Mistral Large.
- Nemotron 3.5 Lightning accepts more context: 262K tokens versus 131K.
Side by side
| Mistral Large | Nemotron 3.5 Lightning | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 31.9 | 40.0 |
| Released | 2024-02-26 | 2026-08-11 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 16K | 262K |
| Input $ / M tokens | $2 | $0.05 |
| Output $ / M tokens | $6 | $0.20 |
| Results tracked | 51 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3.5 Lightning leads
Mistral Large: 34.3 (#240), Nemotron 3.5 Lightning: 40.4 (#141)
| Benchmark | Mistral Large | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Coding | 1277 | 1375 |
| 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), Nemotron 3.5 Lightning: —
| Benchmark | Mistral Large | Nemotron 3.5 Lightning |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Nemotron 3.5 Lightning leads
Mistral Large: 15.8 (#310), Nemotron 3.5 Lightning: 26.8 (#127)
| Benchmark | Mistral Large | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1337 |
| 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 Nemotron 3.5 Lightning leads
Mistral Large: 18.2 (#291), Nemotron 3.5 Lightning: 37.5 (#155)
| Benchmark | Mistral Large | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Math | 1262 | 1359 |
| 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 Nemotron 3.5 Lightning leads
Mistral Large: 30.1 (#230), Nemotron 3.5 Lightning: 37.5 (#154)
| Benchmark | Mistral Large | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Expert | 1232 | 1356 |
| GPQA Diamond | 51.3% | — |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multilingual Nemotron 3.5 Lightning leads
Mistral Large: 40.0 (#219), Nemotron 3.5 Lightning: 44.0 (#180)
| Benchmark | Mistral Large | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Non-English | 1237 | 1295 |
| LMArena Chinese | 1240 | 1359 |
| LMArena French | 1325 | 1366 |
| LMArena German | 1254 | 1282 |
| LMArena Japanese | 1188 | 1206 |
| LMArena Korean | 1202 | 1238 |
| LMArena Russian | 1257 | 1253 |
| LMArena Spanish | 1268 | 1345 |
Instruction Following Nemotron 3.5 Lightning leads
Mistral Large: 67.9 (#191), Nemotron 3.5 Lightning: 69.6 (#170)
| Benchmark | Mistral Large | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Instruction Following | 1249 | 1318 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Nemotron 3.5 Lightning leads
Mistral Large: 38.3 (#199), Nemotron 3.5 Lightning: 39.9 (#165)
| Benchmark | Mistral Large | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Longer Query | 1261 | 1314 |
Writing & Preference Nemotron 3.5 Lightning leads
Mistral Large: 40.7 (#242), Nemotron 3.5 Lightning: 48.5 (#201)
| Benchmark | Mistral Large | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Text | 1266 | 1327 |
| LMArena Creative Writing | 1243 | 1254 |
| EQ-Bench Creative Writing | 985 | 1280 |
| LMArena Multi-Turn | 1260 | 1328 |
| Short-Story Creative Writing | 69% | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Nemotron 3.5 Lightning?
Nemotron 3.5 Lightning is the stronger model overall, scoring 40.0 to 31.9 on the Noometry Index.
Which is cheaper, Mistral Large or Nemotron 3.5 Lightning?
Nemotron 3.5 Lightning is cheaper. It lists at $0.05 per million input tokens and $0.20 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Nemotron 3.5 Lightning better for coding?
Nemotron 3.5 Lightning scores higher on coding benchmarks: 40.4 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3.5 Lightning does, with 262K tokens against 131K.
How many benchmarks do Mistral Large and Nemotron 3.5 Lightning share?
18 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Nemotron 3.5 Lightning has 18.