Model comparison
Codestral vs Nova Premier 1.0
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 30.6 on the Noometry Index. Codestral costs 11× less per token, which makes it the better buy when Nova Premier 1.0's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and Nova Premier 1.0 in 1 category; one gap is clear of the uncertainty.
- The widest gap is in reasoning, where Nova Premier 1.0 leads 23.0 to 19.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 32.5% for Codestral and 44.8% for Nova Premier 1.0.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
- Nova Premier 1.0 accepts more context: 1M tokens versus 256K.
Side by side
| Codestral | Nova Premier 1.0 | |
|---|---|---|
| Provider | Mistral AI | Amazon |
| Noometry Index | 30.6 | 38.3 |
| Released | 2024-05-29 | 2025-04-30 |
| Weights | Proprietary | Proprietary |
| Context window | 256K | 1M |
| Max output | 8K | 10K |
| Input $ / M tokens | $0.30 | $2.50 |
| Output $ / M tokens | $0.90 | $12.50 |
| Results tracked | 7 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Codestral: 27.3 (#321), Nova Premier 1.0: —
| Benchmark | Codestral | Nova Premier 1.0 |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Nova Premier 1.0 leads
Codestral: 19.8 (#251), Nova Premier 1.0: 23.0 (#185)
| Benchmark | Codestral | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | 44.8% |
Math Not comparable
Codestral: —, Nova Premier 1.0: 33.8 (#199)
| Benchmark | Codestral | Nova Premier 1.0 |
|---|---|---|
| Omni-MATH | — | 35% |
Knowledge Not comparable
Codestral: —, Nova Premier 1.0: 35.8 (#180)
| Benchmark | Codestral | Nova Premier 1.0 |
|---|---|---|
| MMLU-Pro | — | 72.6% |
| GPQA (HELM) | — | 51.8% |
Instruction Following Not comparable
Codestral: —, Nova Premier 1.0: 66.8 (#204)
| Benchmark | Codestral | Nova Premier 1.0 |
|---|---|---|
| IFEval | — | 80.3% |
Writing & Preference Not comparable
Codestral: —, Nova Premier 1.0: 51.0 (#178)
| Benchmark | Codestral | Nova Premier 1.0 |
|---|---|---|
| WildBench | — | 78.8% |
Frequently asked questions
Is Codestral better than Nova Premier 1.0?
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 30.6 on the Noometry Index. Codestral costs 11× less per token, which makes it the better buy when Nova Premier 1.0's lead doesn't matter for your workload.
Which is cheaper, Codestral or Nova Premier 1.0?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.
Which has the bigger context window?
Nova Premier 1.0 does, with 1M tokens against 256K.
How many benchmarks do Codestral and Nova Premier 1.0 share?
1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and Nova Premier 1.0 has 6.