Model comparison
Mixtral 8x22B vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 27.1 on the Noometry Index.
Last verified . 16 shared benchmarks.
Mistral AI
NVIDIASummary
- They share 16 benchmarks with published results for both. Mixtral 8x22B scores higher in 1 category and Nemotron 3 Super in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Super leads 38.9 to 15.1.
- The biggest single-benchmark swing is WeirdML: 3.2% for Mixtral 8x22B and 38% for Nemotron 3 Super.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Nemotron 3 Super accepts more context: 262K tokens versus 64K.
Side by side
| Mixtral 8x22B | Nemotron 3 Super | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 27.1 | 40.1 |
| Released | 2024-04-17 | 2026-03-11 |
| Weights | Open | Open |
| Context window | 64K | 262K |
| Max output | 64K | 131K |
| Input $ / M tokens | $2 | $0.08 |
| Output $ / M tokens | $6 | $0.45 |
| Results tracked | 34 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Mixtral 8x22B: 24.2 (#329), Nemotron 3 Super: 39.4 (#158)
| Benchmark | Mixtral 8x22B | Nemotron 3 Super |
|---|---|---|
| WeirdML | 3.2% | 38% |
| LMArena Coding | 1166 | 1403 |
| SciCode | — | 36% |
| BigCodeBench Instruct | 40.6% | — |
| BigCodeBench Complete | 50.2% | — |
| ALE-Bench | — | 213.9 |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |
Agentic & Tool Use Not comparable
Mixtral 8x22B: 23.1 (#127), Nemotron 3 Super: —
| Benchmark | Mixtral 8x22B | Nemotron 3 Super |
|---|---|---|
| Cybench | 7.5% | — |
Reasoning Mixtral 8x22B leads
Mixtral 8x22B: 19.9 (#248), Nemotron 3 Super: 18.7 (#276)
| Benchmark | Mixtral 8x22B | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1386 |
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |
| DTBench | 55.1% | — |
| Epoch Capabilities Index | 122.03 | — |
| ForecastBench | 56.3 | — |
Math Nemotron 3 Super leads
Mixtral 8x22B: 22.9 (#275), Nemotron 3 Super: 39.6 (#101)
| Benchmark | Mixtral 8x22B | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1184 | 1380 |
| MathArena Final-Answer Competitions | — | 60.4% |
| Omni-MATH | 16.3% | — |
| MATH Level 5 | 24.2% | — |
Knowledge Nemotron 3 Super leads
Mixtral 8x22B: 15.1 (#293), Nemotron 3 Super: 38.9 (#139)
| Benchmark | Mixtral 8x22B | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1113 | 1398 |
| GPQA Diamond | 34.1% | — |
| MMLU-Pro | 46% | — |
| GPQA (HELM) | 33.4% | — |
| MMLU | 77.8% | — |
Multilingual Nemotron 3 Super leads
Mixtral 8x22B: 32.8 (#255), Nemotron 3 Super: 48.4 (#144)
| Benchmark | Mixtral 8x22B | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1128 | 1355 |
| LMArena Chinese | 1116 | 1432 |
| LMArena French | 1166 | 1405 |
| LMArena German | 1141 | 1341 |
| LMArena Russian | 1158 | 1336 |
| LMArena Spanish | 1151 | 1417 |
| LMArena Japanese | 1037 | — |
| LMArena Korean | 1057 | — |
Instruction Following Nemotron 3 Super leads
Mixtral 8x22B: 57.7 (#266), Nemotron 3 Super: 71.2 (#154)
| Benchmark | Mixtral 8x22B | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1147 | 1347 |
| IFEval | 72.4% | — |
Long Context Nemotron 3 Super leads
Mixtral 8x22B: 34.7 (#247), Nemotron 3 Super: 41.5 (#139)
| Benchmark | Mixtral 8x22B | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1144 | 1362 |
Writing & Preference Nemotron 3 Super leads
Mixtral 8x22B: 36.9 (#262), Nemotron 3 Super: 55.9 (#140)
| Benchmark | Mixtral 8x22B | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1162 | 1378 |
| LMArena Creative Writing | 1141 | 1317 |
| LMArena Multi-Turn | 1130 | 1369 |
| WildBench | 71.1% | — |
Frequently asked questions
Is Mixtral 8x22B better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 27.1 on the Noometry Index.
Which is cheaper, Mixtral 8x22B or Nemotron 3 Super?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is Mixtral 8x22B or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Super does, with 262K tokens against 64K.
How many benchmarks do Mixtral 8x22B and Nemotron 3 Super share?
16 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Nemotron 3 Super has 21.