Model comparison
gpt-oss-20b vs Magistral Small
gpt-oss-20b is the stronger model overall, scoring 32.5 to 30.2 on the Noometry Index.
Last verified . 8 shared benchmarks.
Mistral AISummary
- They share 8 benchmarks with published results for both. gpt-oss-20b scores higher in 3 categories and Magistral Small in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-20b leads 39.4 to 26.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 53.2% for gpt-oss-20b and 6.3% for Magistral Small.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.50 / $1.50 for Magistral Small.
- gpt-oss-20b accepts more context: 131K tokens versus 128K.
Side by side
| gpt-oss-20b | Magistral Small | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 32.5 | 30.2 |
| Released | 2025-08-05 | 2025-06-10 |
| Weights | Open | Open |
| Context window | 131K | 128K |
| Max output | 16K | 40K |
| Input $ / M tokens | $0.018 | $0.50 |
| Output $ / M tokens | $0.09 | $1.50 |
| Results tracked | 34 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
gpt-oss-20b: 37.6 (#192), Magistral Small: 38.4 (#176)
| Benchmark | gpt-oss-20b | Magistral Small |
|---|---|---|
| SciCode | 34.4% | 35.2% |
| WeirdML | 40.9% | — |
| LMArena Coding | 1306 | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Magistral Small: —
| Benchmark | gpt-oss-20b | Magistral Small |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning gpt-oss-20b leads
gpt-oss-20b: 19.3 (#261), Magistral Small: 6.8 (#350)
| Benchmark | gpt-oss-20b | Magistral Small |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 6.3% |
| CritPt | 1.4% | 0.3% |
| Chess Puzzles | 4% | 3% |
| DTBench | 68% | 61.3% |
| Epoch Capabilities Index | 137.82 | 133.19 |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 5% |
| LMArena Hard Prompts | 1274 | — |
| LMCA | 14.5% | — |
Math gpt-oss-20b leads
gpt-oss-20b: 39.4 (#103), Magistral Small: 26.2 (#261)
| Benchmark | gpt-oss-20b | Magistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 30% |
| Omni-MATH | 56.5% | — |
| LMArena Math | 1317 | — |
Knowledge gpt-oss-20b leads
gpt-oss-20b: 34.6 (#195), Magistral Small: 30.9 (#223)
| Benchmark | gpt-oss-20b | Magistral Small |
|---|---|---|
| GPQA Diamond | 60.8% | 56.1% |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
| LMArena Expert | 1258 | — |
Multilingual Not comparable
gpt-oss-20b: 42.2 (#197), Magistral Small: —
| Benchmark | gpt-oss-20b | Magistral Small |
|---|---|---|
| LMArena Non-English | 1268 | — |
| LMArena Chinese | 1314 | — |
| LMArena German | 1255 | — |
| LMArena Japanese | 1244 | — |
| LMArena Korean | 1236 | — |
| LMArena Russian | 1278 | — |
| LMArena Spanish | 1267 | — |
Instruction Following Not comparable
gpt-oss-20b: 61.8 (#240), Magistral Small: —
| Benchmark | gpt-oss-20b | Magistral Small |
|---|---|---|
| IFEval | 73.2% | — |
| LMArena Instruction Following | 1236 | — |
Long Context Not comparable
gpt-oss-20b: 37.9 (#209), Magistral Small: —
| Benchmark | gpt-oss-20b | Magistral Small |
|---|---|---|
| LMArena Longer Query | 1250 | — |
Writing & Preference Not comparable
gpt-oss-20b: 35.5 (#265), Magistral Small: —
| Benchmark | gpt-oss-20b | Magistral Small |
|---|---|---|
| LMArena Text | 1287 | — |
| LMArena Creative Writing | 1201 | — |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
| LMArena Multi-Turn | 1268 | — |
Frequently asked questions
Is gpt-oss-20b better than Magistral Small?
gpt-oss-20b is the stronger model overall, scoring 32.5 to 30.2 on the Noometry Index.
Which is cheaper, gpt-oss-20b or Magistral Small?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Magistral Small lists at $0.50 and $1.50.
Is gpt-oss-20b or Magistral Small better for coding?
They score almost the same on coding (37.6 vs 38.4); test both on your own repository before choosing.
Which has the bigger context window?
gpt-oss-20b does, with 131K tokens against 128K.
How many benchmarks do gpt-oss-20b and Magistral Small share?
8 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Magistral Small has 10.