Model comparison
gpt-oss-120b vs Magistral Medium
gpt-oss-120b is the stronger model overall, scoring 36.3 to 35.2 on the Noometry Index.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. gpt-oss-120b scores higher in 6 categories and Magistral Medium in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 35.1.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 58.6% for gpt-oss-120b and 16.2% for Magistral Medium.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 131K.
Side by side
| gpt-oss-120b | Magistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 36.3 | 35.2 |
| Released | 2025-08-05 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 41K | 16K |
| Input $ / M tokens | $0.037 | $2 |
| Output $ / M tokens | $0.17 | $5 |
| Results tracked | 48 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
gpt-oss-120b: 33.5 (#256), Magistral Medium: 39.1 (#161)
| Benchmark | gpt-oss-120b | Magistral Medium |
|---|---|---|
| SciCode | 36% | 39.2% |
| LMArena Coding | 1380 | 1319 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Not comparable
gpt-oss-120b: 12.2 (#153), Magistral Medium: —
| Benchmark | gpt-oss-120b | Magistral Medium |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning gpt-oss-120b leads
gpt-oss-120b: 20.0 (#245), Magistral Medium: 8.6 (#348)
| Benchmark | gpt-oss-120b | Magistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 58.6% | 16.2% |
| CritPt | 1.1% | 0.3% |
| LMArena Hard Prompts | 1364 | 1267 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | 22.1% | — |
| ARC-AGI-1 | — | 6.1% |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| Epoch Capabilities Index | 139.93 | — |
Math gpt-oss-120b leads
gpt-oss-120b: 52.5 (#50), Magistral Medium: 35.1 (#189)
| Benchmark | gpt-oss-120b | Magistral Medium |
|---|---|---|
| LMArena Math | 1389 | 1250 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| Omni-MATH | 68.8% | — |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.4 (#96), Magistral Medium: 33.5 (#202)
| Benchmark | gpt-oss-120b | Magistral Medium |
|---|---|---|
| LMArena Expert | 1356 | 1223 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual gpt-oss-120b leads
gpt-oss-120b: 48.0 (#147), Magistral Medium: 39.6 (#224)
| Benchmark | gpt-oss-120b | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1351 | 1232 |
| LMArena Chinese | 1385 | 1227 |
| LMArena French | 1369 | 1267 |
| LMArena German | 1353 | 1248 |
| LMArena Japanese | 1331 | 1175 |
| LMArena Korean | 1282 | 1125 |
| LMArena Russian | 1343 | 1224 |
| LMArena Spanish | 1389 | 1271 |
Instruction Following gpt-oss-120b leads
gpt-oss-120b: 69.3 (#173), Magistral Medium: 66.0 (#211)
| Benchmark | gpt-oss-120b | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1318 | 1254 |
| IFEval | 83.6% | — |
Long Context Magistral Medium leads
gpt-oss-120b: 31.4 (#278), Magistral Medium: 39.3 (#183)
| Benchmark | gpt-oss-120b | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1319 | 1295 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Too close to call
gpt-oss-120b: 46.5 (#217), Magistral Medium: 46.3 (#219)
| Benchmark | gpt-oss-120b | Magistral Medium |
|---|---|---|
| LMArena Text | 1365 | 1255 |
| LMArena Creative Writing | 1275 | 1245 |
| LMArena Multi-Turn | 1340 | 1275 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Magistral Medium?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 35.2 on the Noometry Index.
Which is cheaper, gpt-oss-120b or Magistral Medium?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Magistral Medium lists at $2 and $5.
Is gpt-oss-120b or Magistral Medium better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 131K.
How many benchmarks do gpt-oss-120b and Magistral Medium share?
20 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Magistral Medium has 22.