Model comparison
Codestral vs Llama 3-8B
Codestral is the stronger model overall, scoring 30.6 to 25.5 on the Noometry Index.
Last verified . 4 shared benchmarks.
Mistral AI
MetaSummary
- They share 4 benchmarks with published results for both. Codestral scores higher in 1 category and Llama 3-8B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Codestral leads 19.8 to 14.3.
- The biggest single-benchmark swing is BigCodeBench Complete: 52.5% for Codestral and 36.9% for Llama 3-8B.
- Llama 3-8B has downloadable open weights; the other is API-only.
Side by side
| Codestral | Llama 3-8B | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 30.6 | 25.5 |
| Released | 2024-05-29 | 2024-04-18 |
| Weights | Proprietary | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-8B leads
Codestral: 27.3 (#321), Llama 3-8B: 31.0 (#289)
| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| BigCodeBench Instruct | 41.8% | 31.9% |
| BigCodeBench Complete | 52.5% | 36.9% |
| HumanEval+ | 73.8% | 56.7% |
| MBPP+ | 61.9% | 54.8% |
| Aider Polyglot | 11.1% | — |
| LMArena Coding | — | 1152 |
| ALE-Bench | 137.78 | — |
Reasoning Codestral leads
Codestral: 19.8 (#251), Llama 3-8B: 14.3 (#326)
| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1133 |
| DTBench | — | 43.9% |
| Adversarial NLI | — | 57.3% |
| Epoch Capabilities Index | — | 116.45 |
| ForecastBench | — | 58.6 |
| WinoGrande | — | 75.7% |
Math Not comparable
Codestral: —, Llama 3-8B: 8.8 (#323)
| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 1.9% |
| LMArena Math | — | 1151 |
| MATH Level 5 | — | 6.1% |
Knowledge Not comparable
Codestral: —, Llama 3-8B: 7.8 (#308)
| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| GPQA Diamond | — | 26.1% |
| LMArena Expert | — | 1113 |
| ARC (AI2) Challenge | — | 82.8% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |
Multilingual Not comparable
Codestral: —, Llama 3-8B: 30.8 (#261)
| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| LMArena Non-English | — | 1098 |
| LMArena Chinese | — | 1076 |
| LMArena French | — | 1159 |
| LMArena German | — | 1104 |
| LMArena Japanese | — | 967 |
| LMArena Korean | — | 1004 |
| LMArena Russian | — | 1109 |
| LMArena Spanish | — | 1173 |
Instruction Following Not comparable
Codestral: —, Llama 3-8B: 58.4 (#260)
| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | — | 1127 |
Long Context Not comparable
Codestral: —, Llama 3-8B: 34.2 (#251)
| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | — | 1128 |
Writing & Preference Not comparable
Codestral: —, Llama 3-8B: 37.5 (#256)
| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| LMArena Text | — | 1166 |
| LMArena Creative Writing | — | 1150 |
| LMArena Multi-Turn | — | 1152 |
Frequently asked questions
Is Codestral better than Llama 3-8B?
Codestral is the stronger model overall, scoring 30.6 to 25.5 on the Noometry Index.
Is Codestral or Llama 3-8B better for coding?
Llama 3-8B scores higher on coding benchmarks: 31.0 versus 27.3 in the Noometry coding category.
How many benchmarks do Codestral and Llama 3-8B share?
4 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Llama 3-8B has 34.