# gpt-oss-20b vs MiMo-V2.6-Pro

> MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 to 32.1 on the Noometry Index. gpt-oss-20b costs 15× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-oss-20b-vs-mimo-v2-6-pro
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and MiMo-V2.6-Pro in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.6-Pro leads 66.9 to 35.8.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 131K.

## Snapshot

| | gpt-oss-20b | MiMo-V2.6-Pro |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 32.1 | 46.7 |
| Rank | 249 | 55 |
| Context | 131K | 1.05M |
| Input $/M | $0.018 | $0.43 |
| Output $/M | $0.09 | $0.87 |
| Weights | Open | Open |

## Coding

- gpt-oss-20b: 37.1 (#185)
- MiMo-V2.6-Pro: 53.2 (#27)

| Benchmark | gpt-oss-20b | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Coding | 1307 | 1538 |
| LMArena WebDev | — | 1618 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |

## Agentic & Tool Use

- gpt-oss-20b: 9.2 (#146)
- MiMo-V2.6-Pro: —

| Benchmark | gpt-oss-20b | MiMo-V2.6-Pro |
|---|---|---|
| Terminal-Bench | 3.4% | — |

## Reasoning

- gpt-oss-20b: 18.8 (#251)
- MiMo-V2.6-Pro: 30.4 (#76)

| Benchmark | gpt-oss-20b | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1511 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.81 | — |

## Math

- gpt-oss-20b: 37.6 (#93)
- MiMo-V2.6-Pro: 37.9 (#91)

| Benchmark | gpt-oss-20b | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1317 | 1497 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |

## Knowledge

- gpt-oss-20b: 34.6 (#186)
- MiMo-V2.6-Pro: 43.0 (#85)

| Benchmark | gpt-oss-20b | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1258 | 1548 |
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |

## Multimodal

- gpt-oss-20b: —
- MiMo-V2.6-Pro: 40.2 (#40)

| Benchmark | gpt-oss-20b | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1265 |

## Multilingual

- gpt-oss-20b: 42.4 (#192)
- MiMo-V2.6-Pro: 57.0 (#15)

| Benchmark | gpt-oss-20b | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1269 | 1474 |
| LMArena Chinese | 1311 | 1532 |
| LMArena Russian | 1279 | 1481 |
| LMArena German | 1249 | — |
| LMArena Japanese | 1245 | — |
| LMArena Korean | 1239 | — |
| LMArena Spanish | 1267 | — |

## Instruction Following

- gpt-oss-20b: 62.0 (#235)
- MiMo-V2.6-Pro: 78.2 (#10)

| Benchmark | gpt-oss-20b | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1236 | 1490 |
| IFEval | 73.2% | — |

## Long Context

- gpt-oss-20b: 37.9 (#203)
- MiMo-V2.6-Pro: 46.0 (#26)

| Benchmark | gpt-oss-20b | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1251 | 1500 |

## Writing & Preference

- gpt-oss-20b: 35.8 (#260)
- MiMo-V2.6-Pro: 66.9 (#32)

| Benchmark | gpt-oss-20b | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1288 | 1491 |
| LMArena Creative Writing | 1201 | 1465 |
| LMArena Multi-Turn | 1268 | 1463 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |

## FAQ

### Is gpt-oss-20b better than MiMo-V2.6-Pro?

MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 to 32.1 on the Noometry Index. gpt-oss-20b costs 15× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.

### Which is cheaper, gpt-oss-20b or MiMo-V2.6-Pro?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.

### Is gpt-oss-20b or MiMo-V2.6-Pro better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 53.2 versus 37.1 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.6-Pro does, with 1.05M tokens against 131K.

### How many benchmarks do gpt-oss-20b and MiMo-V2.6-Pro share?

12 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and MiMo-V2.6-Pro has 14.