Model comparison
Codestral vs Llama 3-70B
Codestral is the stronger model overall, scoring 30.1 to 28.5 on the Noometry Index.
Last verified . 5 shared benchmarks.
Mistral AI
MetaSummary
- They share 5 benchmarks with published results for both. Codestral scores higher in 1 category and Llama 3-70B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Llama 3-70B leads 35.3 to 26.9.
Side by side
| Codestral | Llama 3-70B | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 30.1 | 28.5 |
| Released | 2024-05-29 | 2024-04-18 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Codestral: 26.9 (#316), Llama 3-70B: 35.3 (#215)
| Benchmark | Codestral | Llama 3-70B |
|---|---|---|
| BigCodeBench Instruct | 41.8% | 43.6% |
| BigCodeBench Complete | 52.5% | 54.5% |
| HumanEval+ | 73.8% | 72% |
| MBPP+ | 61.9% | 69% |
| Aider Polyglot | 11.1% | — |
| LMArena Coding | — | 1206 |
| ALE-Bench | 137.78 | — |
Agentic & Tool Use Not comparable
Codestral: —, Llama 3-70B: 20.9 (#132)
| Benchmark | Codestral | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Codestral leads
Codestral: 19.1 (#244), Llama 3-70B: 17.4 (#284)
| Benchmark | Codestral | Llama 3-70B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | 35.1% |
| LMArena Hard Prompts | — | 1195 |
| DTBench | — | 54.2% |
| Epoch Capabilities Index | — | 122.91 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math Not comparable
Codestral: —, Llama 3-70B: 12.0 (#299)
| Benchmark | Codestral | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| LMArena Math | — | 1218 |
| MATH Level 5 | — | 22.6% |
Knowledge Not comparable
Codestral: —, Llama 3-70B: 20.8 (#272)
| Benchmark | Codestral | Llama 3-70B |
|---|---|---|
| GPQA Diamond | — | 40.6% |
| LMArena Expert | — | 1149 |
| MMLU | — | 79.3% |
Multilingual Not comparable
Codestral: —, Llama 3-70B: 33.8 (#246)
| Benchmark | Codestral | Llama 3-70B |
|---|---|---|
| LMArena Non-English | — | 1142 |
| LMArena Chinese | — | 1114 |
| LMArena French | — | 1231 |
| LMArena German | — | 1169 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Russian | — | 1159 |
| LMArena Spanish | — | 1241 |
Instruction Following Not comparable
Codestral: —, Llama 3-70B: 62.8 (#233)
| Benchmark | Codestral | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | — | 1194 |
Long Context Not comparable
Codestral: —, Llama 3-70B: 35.6 (#235)
| Benchmark | Codestral | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | — | 1174 |
Writing & Preference Not comparable
Codestral: —, Llama 3-70B: 43.0 (#225)
| Benchmark | Codestral | Llama 3-70B |
|---|---|---|
| LMArena Text | — | 1221 |
| LMArena Creative Writing | — | 1210 |
| LMArena Multi-Turn | — | 1223 |
Frequently asked questions
Is Codestral better than Llama 3-70B?
Codestral is the stronger model overall, scoring 30.1 to 28.5 on the Noometry Index.
Is Codestral or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.3 versus 26.9 in the Noometry coding category.
How many benchmarks do Codestral and Llama 3-70B share?
5 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Llama 3-70B has 31.