Model comparison
Claude 3 Sonnet vs Codestral
Codestral is the stronger model overall, scoring 30.6 to 29.0 on the Noometry Index.
Last verified . 4 shared benchmarks.
Mistral AISummary
- They share 4 benchmarks with published results for both. Claude 3 Sonnet scores higher in 2 categories and Codestral in 0 categories; one gap is clear of the uncertainty.
Side by side
| Claude 3 Sonnet | Codestral | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 29.0 | 30.6 |
| Released | 2024-02-29 | 2024-05-29 |
| Weights | Proprietary | Proprietary |
| Context window | — | 256K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $0.90 |
| Results tracked | 30 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3 Sonnet leads
Claude 3 Sonnet: 29.6 (#302), Codestral: 27.3 (#321)
| Benchmark | Claude 3 Sonnet | Codestral |
|---|---|---|
| BigCodeBench Instruct | 42.7% | 41.8% |
| BigCodeBench Complete | 53.8% | 52.5% |
| HumanEval+ | 64% | 73.8% |
| MBPP+ | 69.3% | 61.9% |
| Aider Polyglot | — | 11.1% |
| WeirdML | 10.2% | — |
| LMArena Coding | 1223 | — |
| ALE-Bench | — | 137.78 |
Reasoning Too close to call
Claude 3 Sonnet: 20.5 (#237), Codestral: 19.8 (#251)
| Benchmark | Claude 3 Sonnet | Codestral |
|---|---|---|
| Kagi LLM Benchmark | — | 32.5% |
| LMArena Hard Prompts | 1197 | — |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.7 | — |
| WinoGrande | 75.1% | — |
Math Not comparable
Claude 3 Sonnet: 10.7 (#310), Codestral: —
| Benchmark | Claude 3 Sonnet | Codestral |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LMArena Math | 1213 | — |
| MATH Level 5 | 18.2% | — |
Knowledge Not comparable
Claude 3 Sonnet: 21.1 (#276), Codestral: —
| Benchmark | Claude 3 Sonnet | Codestral |
|---|---|---|
| GPQA Diamond | 40.6% | — |
| LMArena Expert | 1173 | — |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), Codestral: —
| Benchmark | Claude 3 Sonnet | Codestral |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Not comparable
Claude 3 Sonnet: 37.8 (#234), Codestral: —
| Benchmark | Claude 3 Sonnet | Codestral |
|---|---|---|
| LMArena Non-English | 1205 | — |
| LMArena Chinese | 1189 | — |
| LMArena French | 1229 | — |
| LMArena German | 1204 | — |
| LMArena Japanese | 1131 | — |
| LMArena Korean | 1128 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1204 | — |
Instruction Following Not comparable
Claude 3 Sonnet: 62.8 (#235), Codestral: —
| Benchmark | Claude 3 Sonnet | Codestral |
|---|---|---|
| LMArena Instruction Following | 1199 | — |
Long Context Not comparable
Claude 3 Sonnet: 36.7 (#228), Codestral: —
| Benchmark | Claude 3 Sonnet | Codestral |
|---|---|---|
| LMArena Longer Query | 1211 | — |
Writing & Preference Not comparable
Claude 3 Sonnet: 42.1 (#238), Codestral: —
| Benchmark | Claude 3 Sonnet | Codestral |
|---|---|---|
| LMArena Text | 1218 | — |
| LMArena Creative Writing | 1186 | — |
| LMArena Multi-Turn | 1227 | — |
Frequently asked questions
Is Claude 3 Sonnet better than Codestral?
Codestral is the stronger model overall, scoring 30.6 to 29.0 on the Noometry Index.
Is Claude 3 Sonnet or Codestral better for coding?
Claude 3 Sonnet scores higher on coding benchmarks: 29.6 versus 27.3 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Codestral share?
4 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Codestral has 7.