Model comparison
Codestral vs Phi-4 Mini
Codestral and Phi-4 Mini score almost the same on the Noometry Index (30.6 vs 30.9), so choose on price, context window or the category you care about most.
Last verified . 0 shared benchmarks.
Mistral AI
MicrosoftSummary
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Codestral accepts more context: 256K tokens versus 128K.
- Phi-4 Mini has downloadable open weights; the other is API-only.
Side by side
| Codestral | Phi-4 Mini | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 30.6 | 30.9 |
| Released | 2024-05-29 | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | 256K | 128K |
| Max output | 8K | 4K |
| Input $ / M tokens | $0.30 | $0.075 |
| Output $ / M tokens | $0.90 | $0.30 |
| Results tracked | 7 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Codestral: 27.3 (#321), Phi-4 Mini: 28.1 (#317)
| Benchmark | Codestral | Phi-4 Mini |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| SciCode | — | 10.8% |
| BigCodeBench Instruct | 41.8% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Phi-4 Mini leads
Codestral: 19.8 (#251), Phi-4 Mini: 22.4 (#195)
| Benchmark | Codestral | Phi-4 Mini |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| CritPt | — | 0% |
Knowledge Not comparable
Codestral: —, Phi-4 Mini: 25.3 (#262)
| Benchmark | Codestral | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | — | 23.5% |
Frequently asked questions
Is Codestral better than Phi-4 Mini?
Codestral and Phi-4 Mini score almost the same on the Noometry Index (30.6 vs 30.9), so choose on price, context window or the category you care about most.
Which is cheaper, Codestral or Phi-4 Mini?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Codestral lists at $0.30 and $0.90.
Is Codestral or Phi-4 Mini better for coding?
They score almost the same on coding (27.3 vs 28.1); test both on your own repository before choosing.
Which has the bigger context window?
Codestral does, with 256K tokens against 128K.
How many benchmarks do Codestral and Phi-4 Mini share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Phi-4 Mini has 3.