Model comparison
Codestral vs Granite 3.1 2b Instruct
Granite 3.1 2b Instruct is the stronger model overall, scoring 32.6 to 30.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in coding, where Granite 3.1 2b Instruct leads 32.9 to 26.9.
Side by side
| Codestral | Granite 3.1 2b Instruct | |
|---|---|---|
| Provider | Mistral AI | IBM |
| Noometry Index | 30.1 | 32.6 |
| Released | 2024-05-29 | — |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 3.1 2b Instruct leads
Codestral: 26.9 (#316), Granite 3.1 2b Instruct: 32.9 (#255)
| Benchmark | Codestral | Granite 3.1 2b Instruct |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1149 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Granite 3.1 2b Instruct leads
Codestral: 19.1 (#244), Granite 3.1 2b Instruct: 21.0 (#206)
| Benchmark | Codestral | Granite 3.1 2b Instruct |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1138 |
Math Not comparable
Codestral: —, Granite 3.1 2b Instruct: 30.6 (#206)
| Benchmark | Codestral | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Math | — | 1159 |
Knowledge Not comparable
Codestral: —, Granite 3.1 2b Instruct: 30.3 (#223)
| Benchmark | Codestral | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Expert | — | 1131 |
Multilingual Not comparable
Codestral: —, Granite 3.1 2b Instruct: 29.2 (#264)
| Benchmark | Codestral | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Non-English | — | 1068 |
| LMArena Chinese | — | 1138 |
| LMArena Russian | — | 1063 |
Instruction Following Not comparable
Codestral: —, Granite 3.1 2b Instruct: 58.0 (#259)
| Benchmark | Codestral | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1116 |
Long Context Not comparable
Codestral: —, Granite 3.1 2b Instruct: 35.0 (#239)
| Benchmark | Codestral | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1155 |
Writing & Preference Not comparable
Codestral: —, Granite 3.1 2b Instruct: 34.3 (#269)
| Benchmark | Codestral | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Text | — | 1127 |
| LMArena Creative Writing | — | 1116 |
| LMArena Multi-Turn | — | 1099 |
Frequently asked questions
Is Codestral better than Granite 3.1 2b Instruct?
Granite 3.1 2b Instruct is the stronger model overall, scoring 32.6 to 30.1 on the Noometry Index.
Is Codestral or Granite 3.1 2b Instruct better for coding?
Granite 3.1 2b Instruct scores higher on coding benchmarks: 32.9 versus 26.9 in the Noometry coding category.
How many benchmarks do Codestral and Granite 3.1 2b Instruct share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Granite 3.1 2b Instruct has 12.