Model comparison
gpt-oss-120b vs MiniMax-M2.1
MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 36.0 on the Noometry Index. gpt-oss-120b costs 7.5× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
MiniMaxSummary
- They share 20 benchmarks with published results for both. gpt-oss-120b scores higher in 3 categories and MiniMax-M2.1 in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where MiniMax-M2.1 leads 27.7 to 12.1.
- The biggest single-benchmark swing is Terminal-Bench: 18.7% for gpt-oss-120b and 36.6% for MiniMax-M2.1.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
- MiniMax-M2.1 accepts more context: 205K tokens versus 131K.
Side by side
| gpt-oss-120b | MiniMax-M2.1 | |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 36.0 | 38.4 |
| Released | 2025-08-05 | 2025-12-23 |
| Weights | Open | Open |
| Context window | 131K | 205K |
| Max output | 41K | 131K |
| Input $ / M tokens | $0.037 | $0.30 |
| Output $ / M tokens | $0.17 | $1.20 |
| Results tracked | 48 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
gpt-oss-120b: 33.2 (#251), MiniMax-M2.1: 40.1 (#132)
| Benchmark | gpt-oss-120b | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1380 | 1421 |
| ALE-Bench | 575.62 | 623.83 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| LMArena WebDev | — | 1384 |
| SciCode | 36% | — |
| WeirdML | 48.2% | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use MiniMax-M2.1 leads
gpt-oss-120b: 12.1 (#145), MiniMax-M2.1: 27.7 (#91)
| Benchmark | gpt-oss-120b | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | 18.7% | 36.6% |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning gpt-oss-120b leads
gpt-oss-120b: 19.5 (#236), MiniMax-M2.1: 15.8 (#301)
| Benchmark | gpt-oss-120b | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1410 |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| NYT Connections (extended) | — | 11.2% |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| Epoch Capabilities Index | 139.94 | — |
Math gpt-oss-120b leads
gpt-oss-120b: 50.6 (#43), MiniMax-M2.1: 35.6 (#142)
| Benchmark | gpt-oss-120b | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1388 | 1396 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| Omni-MATH | 68.8% | — |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.3 (#89), MiniMax-M2.1: 37.7 (#143)
| Benchmark | gpt-oss-120b | MiniMax-M2.1 |
|---|---|---|
| Vectara Hallucination Rate | 14.2% | 11.8% |
| LMArena Expert | 1356 | 1432 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual MiniMax-M2.1 leads
gpt-oss-120b: 48.2 (#142), MiniMax-M2.1: 50.2 (#123)
| Benchmark | gpt-oss-120b | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1350 | 1378 |
| LMArena Chinese | 1384 | 1430 |
| LMArena French | 1370 | 1405 |
| LMArena German | 1355 | 1380 |
| LMArena Japanese | 1332 | 1287 |
| LMArena Korean | 1283 | 1297 |
| LMArena Russian | 1343 | 1386 |
| LMArena Spanish | 1388 | 1396 |
Instruction Following MiniMax-M2.1 leads
gpt-oss-120b: 69.5 (#168), MiniMax-M2.1: 74.0 (#108)
| Benchmark | gpt-oss-120b | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1318 | 1399 |
| IFEval | 83.6% | — |
Long Context MiniMax-M2.1 leads
gpt-oss-120b: 31.4 (#273), MiniMax-M2.1: 43.2 (#98)
| Benchmark | gpt-oss-120b | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1319 | 1416 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference MiniMax-M2.1 leads
gpt-oss-120b: 46.7 (#213), MiniMax-M2.1: 58.5 (#114)
| Benchmark | gpt-oss-120b | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1366 | 1392 |
| LMArena Creative Writing | 1274 | 1362 |
| LMArena Multi-Turn | 1340 | 1396 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than MiniMax-M2.1?
MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 36.0 on the Noometry Index. gpt-oss-120b costs 7.5× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-120b or MiniMax-M2.1?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.
Is gpt-oss-120b or MiniMax-M2.1 better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.1 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.1 does, with 205K tokens against 131K.
How many benchmarks do gpt-oss-120b and MiniMax-M2.1 share?
20 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and MiniMax-M2.1 has 22.