Model comparison
Codestral vs Phi 3 Medium 4k Instruct
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 33.0 to 30.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
MicrosoftSummary
- The widest gap is in coding, where Phi 3 Medium 4k Instruct leads 32.9 to 27.3.
- Phi 3 Medium 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Codestral | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 30.6 | 33.0 |
| 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 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi 3 Medium 4k Instruct leads
Codestral: 27.3 (#321), Phi 3 Medium 4k Instruct: 32.9 (#268)
| Benchmark | Codestral | Phi 3 Medium 4k Instruct |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1130 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Phi 3 Medium 4k Instruct leads
Codestral: 19.8 (#251), Phi 3 Medium 4k Instruct: 21.7 (#214)
| Benchmark | Codestral | Phi 3 Medium 4k Instruct |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1127 |
Math Not comparable
Codestral: —, Phi 3 Medium 4k Instruct: 33.4 (#202)
| Benchmark | Codestral | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | — | 1173 |
Knowledge Not comparable
Codestral: —, Phi 3 Medium 4k Instruct: 30.2 (#229)
| Benchmark | Codestral | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | — | 1108 |
Multilingual Not comparable
Codestral: —, Phi 3 Medium 4k Instruct: 30.6 (#263)
| Benchmark | Codestral | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | — | 1094 |
| LMArena Chinese | — | 1108 |
| LMArena French | — | 1110 |
| LMArena German | — | 1101 |
| LMArena Japanese | — | 1042 |
| LMArena Korean | — | 954 |
| LMArena Russian | — | 1145 |
| LMArena Spanish | — | 1095 |
Instruction Following Not comparable
Codestral: —, Phi 3 Medium 4k Instruct: 57.6 (#268)
| Benchmark | Codestral | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1113 |
Long Context Not comparable
Codestral: —, Phi 3 Medium 4k Instruct: 34.0 (#255)
| Benchmark | Codestral | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | — | 1120 |
Writing & Preference Not comparable
Codestral: —, Phi 3 Medium 4k Instruct: 34.1 (#272)
| Benchmark | Codestral | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | — | 1138 |
| LMArena Creative Writing | — | 1107 |
| LMArena Multi-Turn | — | 1088 |
Frequently asked questions
Is Codestral better than Phi 3 Medium 4k Instruct?
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 33.0 to 30.6 on the Noometry Index.
Is Codestral or Phi 3 Medium 4k Instruct better for coding?
Phi 3 Medium 4k Instruct scores higher on coding benchmarks: 32.9 versus 27.3 in the Noometry coding category.
How many benchmarks do Codestral and Phi 3 Medium 4k Instruct share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.