Model comparison
Llama 3.1 Nemotron Ultra 253b v1 vs Mixtral 8x22B
Llama 3.1 Nemotron Ultra 253b v1 is the stronger model overall, scoring 36.7 to 27.1 on the Noometry Index.
Last verified . 10 shared benchmarks.
NVIDIA
Mistral AISummary
- They share 10 benchmarks with published results for both. Llama 3.1 Nemotron Ultra 253b v1 scores higher in 7 categories and Mixtral 8x22B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 3.1 Nemotron Ultra 253b v1 leads 52.2 to 36.9.
Side by side
| Llama 3.1 Nemotron Ultra 253b v1 | Mixtral 8x22B | |
|---|---|---|
| Provider | NVIDIA | Mistral AI |
| Noometry Index | 36.7 | 27.1 |
| Released | — | 2024-04-17 |
| Weights | Open | Open |
| Context window | — | 64K |
| Max output | — | 64K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 11 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 38.4 (#177), Mixtral 8x22B: 24.2 (#329)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1312 | 1166 |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Mixtral 8x22B leads
Llama 3.1 Nemotron Ultra 253b v1: 15.7 (#149), Mixtral 8x22B: 23.1 (#127)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Mixtral 8x22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10% | — |
| Cybench | — | 7.5% |
Reasoning Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 26.3 (#134), Mixtral 8x22B: 19.9 (#248)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1316 | 1150 |
| DTBench | — | 55.1% |
| Epoch Capabilities Index | — | 122.03 |
| ForecastBench | — | 56.3 |
Math Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 37.5 (#152), Mixtral 8x22B: 22.9 (#275)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1360 | 1184 |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
Knowledge Not comparable
Llama 3.1 Nemotron Ultra 253b v1: —, Mixtral 8x22B: 15.1 (#293)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| LMArena Expert | — | 1113 |
| MMLU | — | 77.8% |
Multilingual Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 43.1 (#187), Mixtral 8x22B: 32.8 (#255)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1282 | 1128 |
| LMArena Russian | 1284 | 1158 |
| LMArena Chinese | — | 1116 |
| LMArena French | — | 1166 |
| LMArena German | — | 1141 |
| LMArena Japanese | — | 1037 |
| LMArena Korean | — | 1057 |
| LMArena Spanish | — | 1151 |
Instruction Following Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 69.0 (#178), Mixtral 8x22B: 57.7 (#266)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1308 | 1147 |
| IFEval | — | 72.4% |
Long Context Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 39.5 (#177), Mixtral 8x22B: 34.7 (#247)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1299 | 1144 |
Writing & Preference Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 52.2 (#175), Mixtral 8x22B: 36.9 (#262)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1320 | 1162 |
| LMArena Creative Writing | 1314 | 1141 |
| LMArena Multi-Turn | 1317 | 1130 |
| WildBench | — | 71.1% |
Frequently asked questions
Is Llama 3.1 Nemotron Ultra 253b v1 better than Mixtral 8x22B?
Llama 3.1 Nemotron Ultra 253b v1 is the stronger model overall, scoring 36.7 to 27.1 on the Noometry Index.
Is Llama 3.1 Nemotron Ultra 253b v1 or Mixtral 8x22B better for coding?
Llama 3.1 Nemotron Ultra 253b v1 scores higher on coding benchmarks: 38.4 versus 24.2 in the Noometry coding category.
How many benchmarks do Llama 3.1 Nemotron Ultra 253b v1 and Mixtral 8x22B share?
10 benchmarks have published results for both models. Llama 3.1 Nemotron Ultra 253b v1 has 11 scored results on Noometry and Mixtral 8x22B has 34.