Model comparison
Codestral vs Llama2 70b Steerlm Chat
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 30.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
NVIDIASummary
- Llama2 70b Steerlm Chat has downloadable open weights; the other is API-only.
Side by side
| Codestral | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 30.6 | 31.8 |
| Released | 2024-05-29 | — |
| Weights | Proprietary | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama2 70b Steerlm Chat leads
Codestral: 27.3 (#321), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | Codestral | Llama2 70b Steerlm Chat |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1025 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Too close to call
Codestral: 19.8 (#251), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | Codestral | Llama2 70b Steerlm Chat |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1047 |
Math Not comparable
Codestral: —, Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | Codestral | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | — | 1072 |
Multilingual Not comparable
Codestral: —, Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | Codestral | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | — | 1063 |
Instruction Following Not comparable
Codestral: —, Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | Codestral | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | — | 1060 |
Long Context Not comparable
Codestral: —, Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | Codestral | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | — | 998 |
Writing & Preference Not comparable
Codestral: —, Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | Codestral | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | — | 1098 |
| LMArena Creative Writing | — | 1091 |
| LMArena Multi-Turn | — | 1058 |
Frequently asked questions
Is Codestral better than Llama2 70b Steerlm Chat?
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 30.6 on the Noometry Index.
Is Codestral or Llama2 70b Steerlm Chat better for coding?
Llama2 70b Steerlm Chat scores higher on coding benchmarks: 29.9 versus 27.3 in the Noometry coding category.
How many benchmarks do Codestral and Llama2 70b Steerlm Chat share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Llama2 70b Steerlm Chat has 9.