Model comparison
Llama2 70b Steerlm Chat vs Mistral
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 29.9 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 2 categories and Mistral in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama2 70b Steerlm Chat leads 31.3 to 22.3.
- Llama2 70b Steerlm Chat has downloadable open weights; the other is API-only.
Side by side
| Llama2 70b Steerlm Chat | Mistral | |
|---|---|---|
| Provider | NVIDIA | Mistral AI |
| Noometry Index | 31.8 | 29.9 |
| Released | — | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Llama2 70b Steerlm Chat: 29.9 (#300), Mistral: 33.8 (#250)
| Benchmark | Llama2 70b Steerlm Chat | Mistral |
|---|---|---|
| LMArena Coding | 1025 | 1162 |
Reasoning Mistral leads
Llama2 70b Steerlm Chat: 20.0 (#246), Mistral: 22.2 (#200)
| Benchmark | Llama2 70b Steerlm Chat | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1047 | 1149 |
Math Llama2 70b Steerlm Chat leads
Llama2 70b Steerlm Chat: 31.3 (#226), Mistral: 22.3 (#278)
| Benchmark | Llama2 70b Steerlm Chat | Mistral |
|---|---|---|
| LMArena Math | 1072 | 1180 |
| Omni-MATH | — | 7.2% |
Knowledge Not comparable
Llama2 70b Steerlm Chat: —, Mistral: 16.6 (#288)
| Benchmark | Llama2 70b Steerlm Chat | Mistral |
|---|---|---|
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |
Multilingual Mistral leads
Llama2 70b Steerlm Chat: 28.8 (#270), Mistral: 32.8 (#254)
| Benchmark | Llama2 70b Steerlm Chat | Mistral |
|---|---|---|
| LMArena Non-English | 1063 | 1129 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1180 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |
| LMArena Russian | — | 1168 |
| LMArena Spanish | — | 1143 |
Instruction Following Llama2 70b Steerlm Chat leads
Llama2 70b Steerlm Chat: 54.2 (#279), Mistral: 52.6 (#288)
| Benchmark | Llama2 70b Steerlm Chat | Mistral |
|---|---|---|
| LMArena Instruction Following | 1060 | 1152 |
| IFEval | — | 56.8% |
Long Context Mistral leads
Llama2 70b Steerlm Chat: 30.4 (#288), Mistral: 35.0 (#245)
| Benchmark | Llama2 70b Steerlm Chat | Mistral |
|---|---|---|
| LMArena Longer Query | 998 | 1153 |
Writing & Preference Mistral leads
Llama2 70b Steerlm Chat: 31.6 (#283), Mistral: 37.0 (#260)
| Benchmark | Llama2 70b Steerlm Chat | Mistral |
|---|---|---|
| LMArena Text | 1098 | 1165 |
| LMArena Creative Writing | 1091 | 1158 |
| LMArena Multi-Turn | 1058 | 1147 |
| WildBench | — | 66% |
Frequently asked questions
Is Llama2 70b Steerlm Chat better than Mistral?
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 29.9 on the Noometry Index.
Is Llama2 70b Steerlm Chat or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 29.9 in the Noometry coding category.
How many benchmarks do Llama2 70b Steerlm Chat and Mistral share?
9 benchmarks have published results for both models. Llama2 70b Steerlm Chat has 9 scored results on Noometry and Mistral has 22.