# gpt-oss-20b vs MiMo-V2-Pro

> MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 32.5 on the Noometry Index. gpt-oss-20b costs 15× less per token, which makes it the better buy when MiMo-V2-Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-oss-20b-vs-mimo-v2-pro
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and MiMo-V2-Pro in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Pro leads 62.8 to 35.5.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2-Pro.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 131K.
- gpt-oss-20b has downloadable open weights; the other is API-only.

## Snapshot

| | gpt-oss-20b | MiMo-V2-Pro |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 32.5 | 43.0 |
| Rank | 255 | 103 |
| Context | 131K | 1.05M |
| Input $/M | $0.018 | $0.43 |
| Output $/M | $0.09 | $0.87 |
| Weights | Open | Proprietary |

## Coding

- gpt-oss-20b: 37.6 (#192)
- MiMo-V2-Pro: 43.8 (#83)

| Benchmark | gpt-oss-20b | MiMo-V2-Pro |
|---|---|---|
| LMArena Coding | 1306 | 1476 |
| ALE-Bench | 566.05 | 785.17 |
| LMArena WebDev | — | 1433 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |

## Agentic & Tool Use

- gpt-oss-20b: 9.3 (#154)
- MiMo-V2-Pro: —

| Benchmark | gpt-oss-20b | MiMo-V2-Pro |
|---|---|---|
| Terminal-Bench | 3.4% | — |

## Reasoning

- gpt-oss-20b: 19.3 (#261)
- MiMo-V2-Pro: 22.1 (#206)

| Benchmark | gpt-oss-20b | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1457 |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 25.8% |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| Thematic Generalization | — | 45.9% |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.82 | — |

## Math

- gpt-oss-20b: 39.4 (#103)
- MiMo-V2-Pro: 39.5 (#102)

| Benchmark | gpt-oss-20b | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1317 | 1447 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |

## Knowledge

- gpt-oss-20b: 34.6 (#195)
- MiMo-V2-Pro: 41.4 (#111)

| Benchmark | gpt-oss-20b | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1258 | 1478 |
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |

## Multilingual

- gpt-oss-20b: 42.2 (#197)
- MiMo-V2-Pro: 52.7 (#81)

| Benchmark | gpt-oss-20b | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1268 | 1416 |
| LMArena Chinese | 1314 | 1456 |
| LMArena German | 1255 | 1417 |
| LMArena Japanese | 1244 | 1366 |
| LMArena Korean | 1236 | 1400 |
| LMArena Russian | 1278 | 1427 |
| LMArena Spanish | 1267 | 1457 |
| LMArena French | — | 1469 |

## Instruction Following

- gpt-oss-20b: 61.8 (#240)
- MiMo-V2-Pro: 76.0 (#49)

| Benchmark | gpt-oss-20b | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1236 | 1445 |
| IFEval | 73.2% | — |

## Long Context

- gpt-oss-20b: 37.9 (#209)
- MiMo-V2-Pro: 41.5 (#138)

| Benchmark | gpt-oss-20b | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1250 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |

## Writing & Preference

- gpt-oss-20b: 35.5 (#265)
- MiMo-V2-Pro: 62.8 (#70)

| Benchmark | gpt-oss-20b | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1287 | 1436 |
| LMArena Creative Writing | 1201 | 1415 |
| LMArena Multi-Turn | 1268 | 1456 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |

## FAQ

### Is gpt-oss-20b better than MiMo-V2-Pro?

MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 32.5 on the Noometry Index. gpt-oss-20b costs 15× less per token, which makes it the better buy when MiMo-V2-Pro's lead doesn't matter for your workload.

### Which is cheaper, gpt-oss-20b or MiMo-V2-Pro?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; MiMo-V2-Pro lists at $0.43 and $0.87.

### Is gpt-oss-20b or MiMo-V2-Pro better for coding?

MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 37.6 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2-Pro does, with 1.05M tokens against 131K.

### How many benchmarks do gpt-oss-20b and MiMo-V2-Pro share?

17 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and MiMo-V2-Pro has 23.