Model comparison
Codestral vs Mercury 2.5
Mercury 2.5 is the stronger model overall, scoring 33.5 to 30.6 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and Mercury 2.5 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mercury 2.5 leads 39.5 to 27.3.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Mercury 2.5 accepts more context: 260K tokens versus 256K.
Side by side
| Codestral | Mercury 2.5 | |
|---|---|---|
| Provider | Mistral AI | Inception |
| Noometry Index | 30.6 | 33.5 |
| Released | 2024-05-29 | 2026-09-08 |
| Weights | Proprietary | Proprietary |
| Context window | 256K | 260K |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.30 | $0.04 |
| Output $ / M tokens | $0.90 | $0.15 |
| Results tracked | 7 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2.5 leads
Codestral: 27.3 (#321), Mercury 2.5: 39.5 (#156)
| Benchmark | Codestral | Mercury 2.5 |
|---|---|---|
| ALE-Bench | 137.78 | 301.65 |
| Aider Polyglot | 11.1% | — |
| SciCode | — | 38.5% |
| BigCodeBench Instruct | 41.8% | — |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Mercury 2.5 leads
Codestral: 19.8 (#251), Mercury 2.5: 22.4 (#193)
| Benchmark | Codestral | Mercury 2.5 |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| CritPt | — | 0% |
Math Not comparable
Codestral: —, Mercury 2.5: 23.3 (#272)
| Benchmark | Codestral | Mercury 2.5 |
|---|---|---|
| ProofBench | — | 3% |
Frequently asked questions
Is Codestral better than Mercury 2.5?
Mercury 2.5 is the stronger model overall, scoring 33.5 to 30.6 on the Noometry Index.
Which is cheaper, Codestral or Mercury 2.5?
Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; Codestral lists at $0.30 and $0.90.
Is Codestral or Mercury 2.5 better for coding?
Mercury 2.5 scores higher on coding benchmarks: 39.5 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Mercury 2.5 does, with 260K tokens against 256K.
How many benchmarks do Codestral and Mercury 2.5 share?
1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and Mercury 2.5 has 4.