Model comparison
Grok-3 mini vs Nemotron 3.5 Lightning
Grok-3 mini is the stronger model overall, scoring 41.2 to 40.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
NVIDIASummary
- They share 17 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Nemotron 3.5 Lightning in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Nemotron 3.5 Lightning leads 26.8 to 13.6.
- Nemotron 3.5 Lightning has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Nemotron 3.5 Lightning | |
|---|---|---|
| Provider | xAI | NVIDIA |
| Noometry Index | 41.2 | 40.0 |
| Released | 2025-04-09 | 2026-08-11 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.20 |
| Results tracked | 35 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Grok-3 mini: 40.8 (#131), Nemotron 3.5 Lightning: 40.4 (#141)
| Benchmark | Grok-3 mini | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Coding | 1379 | 1375 |
| Aider Polyglot | 49.3% | — |
| WeirdML | 42.6% | — |
Reasoning Nemotron 3.5 Lightning leads
Grok-3 mini: 13.6 (#334), Nemotron 3.5 Lightning: 26.8 (#127)
| Benchmark | Grok-3 mini | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1337 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| Epoch Capabilities Index | 140.35 | — |
Math Grok-3 mini leads
Grok-3 mini: 42.1 (#85), Nemotron 3.5 Lightning: 37.5 (#155)
| Benchmark | Grok-3 mini | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Math | 1386 | 1359 |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Grok-3 mini leads
Grok-3 mini: 46.4 (#81), Nemotron 3.5 Lightning: 37.5 (#154)
| Benchmark | Grok-3 mini | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Expert | 1395 | 1356 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
Multilingual Grok-3 mini leads
Grok-3 mini: 48.1 (#145), Nemotron 3.5 Lightning: 44.0 (#180)
| Benchmark | Grok-3 mini | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Non-English | 1352 | 1295 |
| LMArena Chinese | 1387 | 1359 |
| LMArena French | 1357 | 1366 |
| LMArena German | 1349 | 1282 |
| LMArena Japanese | 1342 | 1206 |
| LMArena Korean | 1335 | 1238 |
| LMArena Russian | 1353 | 1253 |
| LMArena Spanish | 1381 | 1345 |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), Nemotron 3.5 Lightning: 69.6 (#170)
| Benchmark | Grok-3 mini | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Instruction Following | 1357 | 1318 |
| IFEval | 95.1% | — |
Long Context Grok-3 mini leads
Grok-3 mini: 41.0 (#147), Nemotron 3.5 Lightning: 39.9 (#165)
| Benchmark | Grok-3 mini | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Longer Query | 1372 | 1314 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Grok-3 mini leads
Grok-3 mini: 52.5 (#169), Nemotron 3.5 Lightning: 48.5 (#201)
| Benchmark | Grok-3 mini | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Text | 1370 | 1327 |
| LMArena Creative Writing | 1342 | 1254 |
| LMArena Multi-Turn | 1355 | 1328 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | — | 1280 |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than Nemotron 3.5 Lightning?
Grok-3 mini is the stronger model overall, scoring 41.2 to 40.0 on the Noometry Index.
Is Grok-3 mini or Nemotron 3.5 Lightning better for coding?
They score almost the same on coding (40.8 vs 40.4); test both on your own repository before choosing.
How many benchmarks do Grok-3 mini and Nemotron 3.5 Lightning share?
17 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Nemotron 3.5 Lightning has 18.