Model comparison
GPT-5.3 Codex vs Magistral Small
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 30.2 on the Noometry Index. Magistral Small costs 6.4× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. GPT-5.3 Codex scores higher in 1 category and Magistral Small in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where GPT-5.3 Codex leads 48.6 to 38.4.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
- GPT-5.3 Codex accepts more context: 400K tokens versus 128K.
- Magistral Small has downloadable open weights; the other is API-only.
Side by side
| GPT-5.3 Codex | Magistral Small | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 45.8 | 30.2 |
| Released | 2026-02-05 | 2025-06-10 |
| Weights | Proprietary | Open |
| Context window | 400K | 128K |
| Max output | 128K | 40K |
| Input $ / M tokens | $1.75 | $0.50 |
| Output $ / M tokens | $14 | $1.50 |
| Results tracked | 8 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Codex leads
GPT-5.3 Codex: 48.6 (#56), Magistral Small: 38.4 (#176)
| Benchmark | GPT-5.3 Codex | Magistral Small |
|---|---|---|
| SWE-bench Verified | 74.8% | — |
| LMArena WebDev | 1409 | — |
| SciCode | — | 35.2% |
| WeirdML | 79.3% | — |
| ALE-Bench | 1,655 | — |
Agentic & Tool Use Not comparable
GPT-5.3 Codex: 48.0 (#9), Magistral Small: —
| Benchmark | GPT-5.3 Codex | Magistral Small |
|---|---|---|
| Terminal-Bench | 78.4% | — |
| METR Time Horizons | 74.5% | — |
| Vending-Bench 2 | 5,940 | — |
Reasoning Not comparable
GPT-5.3 Codex: —, Magistral Small: 6.8 (#350)
| Benchmark | GPT-5.3 Codex | Magistral Small |
|---|---|---|
| Epoch Capabilities Index | 156.77 | 133.19 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 6.3% |
| ARC-AGI-1 | — | 5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 3% |
| DTBench | — | 61.3% |
Math Not comparable
GPT-5.3 Codex: —, Magistral Small: 26.2 (#261)
| Benchmark | GPT-5.3 Codex | Magistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 30% |
Knowledge Not comparable
GPT-5.3 Codex: —, Magistral Small: 30.9 (#223)
| Benchmark | GPT-5.3 Codex | Magistral Small |
|---|---|---|
| GPQA Diamond | — | 56.1% |
Frequently asked questions
Is GPT-5.3 Codex better than Magistral Small?
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 30.2 on the Noometry Index. Magistral Small costs 6.4× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.
Which is cheaper, GPT-5.3 Codex or Magistral Small?
Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.
Is GPT-5.3 Codex or Magistral Small better for coding?
GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 38.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5.3 Codex does, with 400K tokens against 128K.
How many benchmarks do GPT-5.3 Codex and Magistral Small share?
1 benchmark has published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and Magistral Small has 10.