Model comparison
Codestral vs GPT-5.3 Chat
GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 30.6 on the Noometry Index. Codestral costs 11× less per token, which makes it the better buy when GPT-5.3 Chat's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in coding, where GPT-5.3 Chat leads 41.4 to 27.3.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Chat.
- Codestral accepts more context: 256K tokens versus 128K.
Side by side
| Codestral | GPT-5.3 Chat | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 30.6 | 42.8 |
| Released | 2024-05-29 | 2026-03-03 |
| Weights | Proprietary | Proprietary |
| Context window | 256K | 128K |
| Max output | 8K | 16K |
| Input $ / M tokens | $0.30 | $1.75 |
| Output $ / M tokens | $0.90 | $14 |
| Results tracked | 7 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Chat leads
Codestral: 27.3 (#321), GPT-5.3 Chat: 41.4 (#124)
| Benchmark | Codestral | GPT-5.3 Chat |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1408 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning GPT-5.3 Chat leads
Codestral: 19.8 (#251), GPT-5.3 Chat: 28.5 (#102)
| Benchmark | Codestral | GPT-5.3 Chat |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1399 |
Math Not comparable
Codestral: —, GPT-5.3 Chat: 38.2 (#142)
| Benchmark | Codestral | GPT-5.3 Chat |
|---|---|---|
| LMArena Math | — | 1389 |
Knowledge Not comparable
Codestral: —, GPT-5.3 Chat: 38.8 (#140)
| Benchmark | Codestral | GPT-5.3 Chat |
|---|---|---|
| LMArena Expert | — | 1397 |
Multilingual Not comparable
Codestral: —, GPT-5.3 Chat: 50.3 (#124)
| Benchmark | Codestral | GPT-5.3 Chat |
|---|---|---|
| LMArena Non-English | — | 1382 |
| LMArena Chinese | — | 1432 |
| LMArena French | — | 1397 |
| LMArena German | — | 1384 |
| LMArena Japanese | — | 1352 |
| LMArena Korean | — | 1346 |
| LMArena Russian | — | 1400 |
| LMArena Spanish | — | 1371 |
Instruction Following Not comparable
Codestral: —, GPT-5.3 Chat: 72.8 (#129)
| Benchmark | Codestral | GPT-5.3 Chat |
|---|---|---|
| LMArena Instruction Following | — | 1378 |
Long Context Not comparable
Codestral: —, GPT-5.3 Chat: 42.6 (#120)
| Benchmark | Codestral | GPT-5.3 Chat |
|---|---|---|
| LMArena Longer Query | — | 1396 |
Writing & Preference Not comparable
Codestral: —, GPT-5.3 Chat: 63.1 (#68)
| Benchmark | Codestral | GPT-5.3 Chat |
|---|---|---|
| LMArena Text | — | 1389 |
| LMArena Creative Writing | — | 1355 |
| EQ-Bench Creative Writing | — | 1690 |
| LMArena Multi-Turn | — | 1412 |
Frequently asked questions
Is Codestral better than GPT-5.3 Chat?
GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 30.6 on the Noometry Index. Codestral costs 11× less per token, which makes it the better buy when GPT-5.3 Chat's lead doesn't matter for your workload.
Which is cheaper, Codestral or GPT-5.3 Chat?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; GPT-5.3 Chat lists at $1.75 and $14.
Is Codestral or GPT-5.3 Chat better for coding?
GPT-5.3 Chat scores higher on coding benchmarks: 41.4 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 GPT-5.3 Chat share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and GPT-5.3 Chat has 18.