Model comparison
Llama2 70b Steerlm Chat vs Mixtral 8x22B
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 27.1 on the Noometry Index.
Last verified . 9 shared benchmarks.
NVIDIA
Mistral AISummary
- They share 9 benchmarks with published results for both. Llama2 70b Steerlm Chat scores higher in 3 categories and Mixtral 8x22B in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama2 70b Steerlm Chat leads 31.3 to 22.9.
Side by side
| Llama2 70b Steerlm Chat | Mixtral 8x22B | |
|---|---|---|
| Provider | NVIDIA | Mistral AI |
| Noometry Index | 31.8 | 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 | 9 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama2 70b Steerlm Chat leads
Llama2 70b Steerlm Chat: 29.9 (#300), Mixtral 8x22B: 24.2 (#329)
| Benchmark | Llama2 70b Steerlm Chat | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1025 | 1166 |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Not comparable
Llama2 70b Steerlm Chat: —, Mixtral 8x22B: 23.1 (#127)
| Benchmark | Llama2 70b Steerlm Chat | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |
Reasoning Too close to call
Llama2 70b Steerlm Chat: 20.0 (#246), Mixtral 8x22B: 19.9 (#248)
| Benchmark | Llama2 70b Steerlm Chat | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1047 | 1150 |
| DTBench | — | 55.1% |
| Epoch Capabilities Index | — | 122.03 |
| ForecastBench | — | 56.3 |
Math Llama2 70b Steerlm Chat leads
Llama2 70b Steerlm Chat: 31.3 (#226), Mixtral 8x22B: 22.9 (#275)
| Benchmark | Llama2 70b Steerlm Chat | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1072 | 1184 |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
Knowledge Not comparable
Llama2 70b Steerlm Chat: —, Mixtral 8x22B: 15.1 (#293)
| Benchmark | Llama2 70b Steerlm Chat | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| LMArena Expert | — | 1113 |
| MMLU | — | 77.8% |
Multilingual Mixtral 8x22B leads
Llama2 70b Steerlm Chat: 28.8 (#270), Mixtral 8x22B: 32.8 (#255)
| Benchmark | Llama2 70b Steerlm Chat | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1063 | 1128 |
| LMArena Chinese | — | 1116 |
| LMArena French | — | 1166 |
| LMArena German | — | 1141 |
| LMArena Japanese | — | 1037 |
| LMArena Korean | — | 1057 |
| LMArena Russian | — | 1158 |
| LMArena Spanish | — | 1151 |
Instruction Following Mixtral 8x22B leads
Llama2 70b Steerlm Chat: 54.2 (#279), Mixtral 8x22B: 57.7 (#266)
| Benchmark | Llama2 70b Steerlm Chat | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1060 | 1147 |
| IFEval | — | 72.4% |
Long Context Mixtral 8x22B leads
Llama2 70b Steerlm Chat: 30.4 (#288), Mixtral 8x22B: 34.7 (#247)
| Benchmark | Llama2 70b Steerlm Chat | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 998 | 1144 |
Writing & Preference Mixtral 8x22B leads
Llama2 70b Steerlm Chat: 31.6 (#283), Mixtral 8x22B: 36.9 (#262)
| Benchmark | Llama2 70b Steerlm Chat | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1098 | 1162 |
| LMArena Creative Writing | 1091 | 1141 |
| LMArena Multi-Turn | 1058 | 1130 |
| WildBench | — | 71.1% |
Frequently asked questions
Is Llama2 70b Steerlm Chat better than Mixtral 8x22B?
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 27.1 on the Noometry Index.
Is Llama2 70b Steerlm Chat or Mixtral 8x22B better for coding?
Llama2 70b Steerlm Chat scores higher on coding benchmarks: 29.9 versus 24.2 in the Noometry coding category.
How many benchmarks do Llama2 70b Steerlm Chat and Mixtral 8x22B share?
9 benchmarks have published results for both models. Llama2 70b Steerlm Chat has 9 scored results on Noometry and Mixtral 8x22B has 34.