Model comparison
Codestral vs Mistral Nemo
Codestral is the stronger model overall, scoring 30.6 to 26.4 on the Noometry Index. Mistral Nemo costs 3.0× less per token, which makes it the better buy when Codestral's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AISummary
- Mistral Nemo is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Codestral accepts more context: 256K tokens versus 128K.
- Mistral Nemo has downloadable open weights; the other is API-only.
Side by side
| Codestral | Mistral Nemo | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 30.6 | 26.4 |
| Released | 2024-05-29 | 2024-07-01 |
| Weights | Proprietary | Open |
| Context window | 256K | 128K |
| Max output | 8K | 128K |
| Input $ / M tokens | $0.30 | $0.15 |
| Output $ / M tokens | $0.90 | $0.15 |
| Results tracked | 7 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Codestral: 27.3 (#321), Mistral Nemo: —
| Benchmark | Codestral | Mistral Nemo |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, Mistral Nemo: 23.5 (#125)
| Benchmark | Codestral | Mistral Nemo |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.6% |
| BALROG | — | 17.6% |
Reasoning Too close to call
Codestral: 19.8 (#251), Mistral Nemo: 20.7 (#232)
| Benchmark | Codestral | Mistral Nemo |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| DTBench | — | 48.6% |
| Epoch Capabilities Index | — | 118.68 |
| PIQA | — | 83.5% |
Math Not comparable
Codestral: —, Mistral Nemo: 25.5 (#268)
| Benchmark | Codestral | Mistral Nemo |
|---|---|---|
| MATH Level 5 | — | 10.8% |
| GSM8K | — | 84.2% |
Knowledge Not comparable
Codestral: —, Mistral Nemo: 12.3 (#298)
| Benchmark | Codestral | Mistral Nemo |
|---|---|---|
| GPQA Diamond | — | 29.9% |
| BoolQ | — | 82.5% |
Writing & Preference Not comparable
Codestral: —, Mistral Nemo: 28.5 (#296)
| Benchmark | Codestral | Mistral Nemo |
|---|---|---|
| EQ-Bench Creative Writing | — | 881 |
Frequently asked questions
Is Codestral better than Mistral Nemo?
Codestral is the stronger model overall, scoring 30.6 to 26.4 on the Noometry Index. Mistral Nemo costs 3.0× less per token, which makes it the better buy when Codestral's lead doesn't matter for your workload.
Which is cheaper, Codestral or Mistral Nemo?
Mistral Nemo is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Codestral lists at $0.30 and $0.90.
Which has the bigger context window?
Codestral does, with 256K tokens against 128K.
How many benchmarks do Codestral and Mistral Nemo share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Mistral Nemo has 10.