Model comparison
gpt-oss-120b vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 36.0 on the Noometry Index. gpt-oss-120b costs 7.7× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. gpt-oss-120b scores higher in 2 categories and MiMo-V2.5-Pro in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.5 to 46.7.
- The biggest single-benchmark swing is SciCode: 36% for gpt-oss-120b and 50.2% for MiMo-V2.5-Pro.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 131K.
Side by side
| gpt-oss-120b | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 36.0 | 44.8 |
| Released | 2025-08-05 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 131K | 1.05M |
| Max output | 41K | 131K |
| Input $ / M tokens | $0.037 | $0.43 |
| Output $ / M tokens | $0.17 | $0.87 |
| Results tracked | 48 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
gpt-oss-120b: 33.2 (#251), MiMo-V2.5-Pro: 47.0 (#58)
| Benchmark | gpt-oss-120b | MiMo-V2.5-Pro |
|---|---|---|
| SciCode | 36% | 50.2% |
| LMArena Coding | 1380 | 1502 |
| ALE-Bench | 575.62 | 899.8 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| LMArena WebDev | — | 1477 |
| WeirdML | 48.2% | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Not comparable
gpt-oss-120b: 12.1 (#145), MiMo-V2.5-Pro: —
| Benchmark | gpt-oss-120b | MiMo-V2.5-Pro |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning MiMo-V2.5-Pro leads
gpt-oss-120b: 19.5 (#236), MiMo-V2.5-Pro: 25.9 (#124)
| Benchmark | gpt-oss-120b | MiMo-V2.5-Pro |
|---|---|---|
| CritPt | 1.1% | 4% |
| LMArena Hard Prompts | 1364 | 1487 |
| DTBench | 76.3% | 84.5% |
| LMCA | 22.1% | 29.5% |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| NYT Connections (extended) | — | 34.4% |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| Surface Evolver Bench | 25% | — |
| Epoch Capabilities Index | 139.94 | — |
Math gpt-oss-120b leads
gpt-oss-120b: 50.6 (#43), MiMo-V2.5-Pro: 38.6 (#84)
| Benchmark | gpt-oss-120b | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1388 | 1480 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | — | 22% |
| Omni-MATH | 68.8% | — |
Knowledge Too close to call
gpt-oss-120b: 42.3 (#89), MiMo-V2.5-Pro: 41.5 (#100)
| Benchmark | gpt-oss-120b | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1356 | 1501 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual MiMo-V2.5-Pro leads
gpt-oss-120b: 48.2 (#142), MiMo-V2.5-Pro: 55.3 (#33)
| Benchmark | gpt-oss-120b | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1350 | 1449 |
| LMArena Chinese | 1384 | 1507 |
| LMArena French | 1370 | 1489 |
| LMArena German | 1355 | 1455 |
| LMArena Japanese | 1332 | 1418 |
| LMArena Korean | 1283 | 1436 |
| LMArena Russian | 1343 | 1450 |
| LMArena Spanish | 1388 | 1470 |
Instruction Following MiMo-V2.5-Pro leads
gpt-oss-120b: 69.5 (#168), MiMo-V2.5-Pro: 77.6 (#21)
| Benchmark | gpt-oss-120b | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1318 | 1477 |
| IFEval | 83.6% | — |
Long Context MiMo-V2.5-Pro leads
gpt-oss-120b: 31.4 (#273), MiMo-V2.5-Pro: 45.4 (#38)
| Benchmark | gpt-oss-120b | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1319 | 1482 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference MiMo-V2.5-Pro leads
gpt-oss-120b: 46.7 (#213), MiMo-V2.5-Pro: 65.5 (#47)
| Benchmark | gpt-oss-120b | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1366 | 1465 |
| LMArena Creative Writing | 1274 | 1440 |
| EQ-Bench Creative Writing | 961 | 1493 |
| LMArena Multi-Turn | 1340 | 1477 |
| Short-Story Creative Writing | 77.1% | — |
| WildBench | 84.5% | — |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is gpt-oss-120b better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 36.0 on the Noometry Index. gpt-oss-120b costs 7.7× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-120b or MiMo-V2.5-Pro?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is gpt-oss-120b or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 131K.
How many benchmarks do gpt-oss-120b and MiMo-V2.5-Pro share?
23 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and MiMo-V2.5-Pro has 27.