Model comparison
Codestral vs Granite 4.1 8b
Granite 4.1 8b is the stronger model overall, scoring 36.8 to 30.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in reasoning, where Granite 4.1 8b leads 24.6 to 19.1.
Side by side
| Codestral | Granite 4.1 8b | |
|---|---|---|
| Provider | Mistral AI | IBM |
| Noometry Index | 30.1 | 36.8 |
| 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 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.1 8b leads
Codestral: 26.9 (#316), Granite 4.1 8b: 29.9 (#291)
| Benchmark | Codestral | Granite 4.1 8b |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1190 |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1313 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Granite 4.1 8b leads
Codestral: 19.1 (#244), Granite 4.1 8b: 24.6 (#142)
| Benchmark | Codestral | Granite 4.1 8b |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1294 |
Math Not comparable
Codestral: —, Granite 4.1 8b: 33.8 (#167)
| Benchmark | Codestral | Granite 4.1 8b |
|---|---|---|
| LMArena Math | — | 1311 |
Knowledge Not comparable
Codestral: —, Granite 4.1 8b: 35.5 (#171)
| Benchmark | Codestral | Granite 4.1 8b |
|---|---|---|
| LMArena Expert | — | 1310 |
Multilingual Not comparable
Codestral: —, Granite 4.1 8b: 41.8 (#199)
| Benchmark | Codestral | Granite 4.1 8b |
|---|---|---|
| LMArena Non-English | — | 1261 |
| LMArena Chinese | — | 1335 |
| LMArena Russian | — | 1238 |
Instruction Following Not comparable
Codestral: —, Granite 4.1 8b: 67.0 (#198)
| Benchmark | Codestral | Granite 4.1 8b |
|---|---|---|
| LMArena Instruction Following | — | 1268 |
Long Context Not comparable
Codestral: —, Granite 4.1 8b: 38.7 (#188)
| Benchmark | Codestral | Granite 4.1 8b |
|---|---|---|
| LMArena Longer Query | — | 1275 |
Writing & Preference Not comparable
Codestral: —, Granite 4.1 8b: 48.3 (#199)
| Benchmark | Codestral | Granite 4.1 8b |
|---|---|---|
| LMArena Text | — | 1291 |
| LMArena Creative Writing | — | 1249 |
| LMArena Multi-Turn | — | 1269 |
Frequently asked questions
Is Codestral better than Granite 4.1 8b?
Granite 4.1 8b is the stronger model overall, scoring 36.8 to 30.1 on the Noometry Index.
Is Codestral or Granite 4.1 8b better for coding?
Granite 4.1 8b scores higher on coding benchmarks: 29.9 versus 26.9 in the Noometry coding category.
How many benchmarks do Codestral and Granite 4.1 8b share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Granite 4.1 8b has 13.