Model comparison
Codestral vs Llama 3.2 90B
Codestral is the stronger model overall, scoring 30.6 to 27.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
MetaSummary
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| Codestral | Llama 3.2 90B | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 30.6 | 27.5 |
| Released | 2024-05-29 | 2024-09-24 |
| 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 Not comparable
Codestral: 27.3 (#321), Llama 3.2 90B: —
| Benchmark | Codestral | Llama 3.2 90B |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, Llama 3.2 90B: 30.0 (#80)
| Benchmark | Codestral | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |
Reasoning Llama 3.2 90B leads
Codestral: 19.8 (#251), Llama 3.2 90B: 21.7 (#217)
| Benchmark | Codestral | Llama 3.2 90B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| EnigmaEval | — | 0.4% |
| Epoch Capabilities Index | — | 125.5 |
Math Not comparable
Codestral: —, Llama 3.2 90B: 11.1 (#308)
| Benchmark | Codestral | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| MATH Level 5 | — | 39.4% |
Knowledge Not comparable
Codestral: —, Llama 3.2 90B: 21.7 (#274)
| Benchmark | Codestral | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| MMLU | — | 80.3% |
Multimodal Not comparable
Codestral: —, Llama 3.2 90B: 25.4 (#124)
| Benchmark | Codestral | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Frequently asked questions
Is Codestral better than Llama 3.2 90B?
Codestral is the stronger model overall, scoring 30.6 to 27.5 on the Noometry Index.
How many benchmarks do Codestral and Llama 3.2 90B share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Llama 3.2 90B has 9.