Model comparison
Codestral vs Granite 3.0 2b Instruct
Codestral and Granite 3.0 2b Instruct score almost the same on the Noometry Index (30.6 vs 30.8), so choose on price, context window or the category you care about most.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and Granite 3.0 2b Instruct in 2 categories; one gap is clear of the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Instruct: 41.8% for Codestral and 20.5% for Granite 3.0 2b Instruct.
- Granite 3.0 2b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codestral | Granite 3.0 2b Instruct | |
|---|---|---|
| Provider | Mistral AI | IBM |
| Noometry Index | 30.6 | 30.8 |
| Released | 2024-05-29 | — |
| Weights | Proprietary | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 3.0 2b Instruct leads
Codestral: 27.3 (#321), Granite 3.0 2b Instruct: 28.3 (#316)
| Benchmark | Codestral | Granite 3.0 2b Instruct |
|---|---|---|
| BigCodeBench Instruct | 41.8% | 20.5% |
| Aider Polyglot | 11.1% | — |
| LMArena Coding | — | 1090 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Too close to call
Codestral: 19.8 (#251), Granite 3.0 2b Instruct: 20.5 (#235)
| Benchmark | Codestral | Granite 3.0 2b Instruct |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1073 |
Math Not comparable
Codestral: —, Granite 3.0 2b Instruct: 32.2 (#217)
| Benchmark | Codestral | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Math | — | 1117 |
Knowledge Not comparable
Codestral: —, Granite 3.0 2b Instruct: 29.0 (#241)
| Benchmark | Codestral | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Expert | — | 1064 |
Multilingual Not comparable
Codestral: —, Granite 3.0 2b Instruct: 27.0 (#278)
| Benchmark | Codestral | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Non-English | — | 1033 |
| LMArena Chinese | — | 1070 |
| LMArena Russian | — | 1045 |
Instruction Following Not comparable
Codestral: —, Granite 3.0 2b Instruct: 53.9 (#284)
| Benchmark | Codestral | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1056 |
Long Context Not comparable
Codestral: —, Granite 3.0 2b Instruct: 32.5 (#268)
| Benchmark | Codestral | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1070 |
Writing & Preference Not comparable
Codestral: —, Granite 3.0 2b Instruct: 29.6 (#292)
| Benchmark | Codestral | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Text | — | 1080 |
| LMArena Creative Writing | — | 1046 |
| LMArena Multi-Turn | — | 1053 |
Frequently asked questions
Is Codestral better than Granite 3.0 2b Instruct?
Codestral and Granite 3.0 2b Instruct score almost the same on the Noometry Index (30.6 vs 30.8), so choose on price, context window or the category you care about most.
Is Codestral or Granite 3.0 2b Instruct better for coding?
Granite 3.0 2b Instruct scores higher on coding benchmarks: 28.3 versus 27.3 in the Noometry coding category.
How many benchmarks do Codestral and Granite 3.0 2b Instruct share?
1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and Granite 3.0 2b Instruct has 13.