Model comparison
Codestral vs Mercury 2
Mercury 2 is the stronger model overall, scoring 39.1 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 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mercury 2 leads 33.5 to 27.3.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Codestral accepts more context: 256K tokens versus 128K.
Side by side
| Codestral | Mercury 2 | |
|---|---|---|
| Provider | Mistral AI | Inception |
| Noometry Index | 30.6 | 39.1 |
| Released | 2024-05-29 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 256K | 128K |
| Max output | 8K | 50K |
| Input $ / M tokens | $0.30 | $0.25 |
| Output $ / M tokens | $0.90 | $0.75 |
| Results tracked | 7 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2 leads
Codestral: 27.3 (#321), Mercury 2: 33.5 (#255)
| Benchmark | Codestral | Mercury 2 |
|---|---|---|
| ALE-Bench | 137.78 | 785.58 |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1391 |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Mercury 2 leads
Codestral: 19.8 (#251), Mercury 2: 23.8 (#170)
| Benchmark | Codestral | Mercury 2 |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| CritPt | — | 0.8% |
| LMArena Hard Prompts | — | 1362 |
Knowledge Not comparable
Codestral: —, Mercury 2: 36.2 (#172)
| Benchmark | Codestral | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | — | 12.3% |
| LMArena Expert | — | 1358 |
Multilingual Not comparable
Codestral: —, Mercury 2: 46.6 (#157)
| Benchmark | Codestral | Mercury 2 |
|---|---|---|
| LMArena Non-English | — | 1331 |
| LMArena Chinese | — | 1417 |
| LMArena Russian | — | 1304 |
Instruction Following Not comparable
Codestral: —, Mercury 2: 70.2 (#165)
| Benchmark | Codestral | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | — | 1329 |
Long Context Not comparable
Codestral: —, Mercury 2: 40.5 (#154)
| Benchmark | Codestral | Mercury 2 |
|---|---|---|
| LMArena Longer Query | — | 1330 |
Writing & Preference Not comparable
Codestral: —, Mercury 2: 53.8 (#155)
| Benchmark | Codestral | Mercury 2 |
|---|---|---|
| LMArena Text | — | 1355 |
| LMArena Creative Writing | — | 1289 |
| LMArena Multi-Turn | — | 1358 |
Frequently asked questions
Is Codestral better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 39.1 to 30.6 on the Noometry Index.
Which is cheaper, Codestral or Mercury 2?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Codestral lists at $0.30 and $0.90.
Is Codestral or Mercury 2 better for coding?
Mercury 2 scores higher on coding benchmarks: 33.5 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Codestral does, with 256K tokens against 128K.
How many benchmarks do Codestral and Mercury 2 share?
1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and Mercury 2 has 17.