# gpt-oss-120b vs Kimi K2.6

> Kimi K2.6 is the stronger model overall, scoring 47.7 to 36.3 on the Noometry Index. gpt-oss-120b costs 24× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-oss-120b-vs-kimi-k2-6
- Last updated: 2026-10-12
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. gpt-oss-120b scores higher in 0 categories and Kimi K2.6 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2.6 leads 68.5 to 46.5.
- The biggest single-benchmark swing is SciCode: 36% for gpt-oss-120b and 53.5% for Kimi K2.6.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- Kimi K2.6 accepts more context: 262K tokens versus 131K.

## Snapshot

| | gpt-oss-120b | Kimi K2.6 |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 36.3 | 47.7 |
| Rank | 217 | 60 |
| Context | 131K | 262K |
| Input $/M | $0.037 | $0.95 |
| Output $/M | $0.17 | $4 |
| Weights | Open | Open |

## Coding

- gpt-oss-120b: 33.5 (#256)
- Kimi K2.6: 50.7 (#43)

| Benchmark | gpt-oss-120b | Kimi K2.6 |
|---|---|---|
| SciCode | 36% | 53.5% |
| WeirdML | 48.2% | 55.9% |
| LMArena Coding | 1380 | 1488 |
| ALE-Bench | 575.62 | 1,093 |
| SWE-bench Verified | — | 76.7% |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| LMArena WebDev | — | 1509 |
| AlgoTune | 1.41 | — |

## Agentic & Tool Use

- gpt-oss-120b: 12.2 (#153)
- Kimi K2.6: 21.9 (#137)

| Benchmark | gpt-oss-120b | Kimi K2.6 |
|---|---|---|
| Vending-Bench 2 | -21.53 | 6,205 |
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| METR Time Horizons | 56.6% | — |

## Reasoning

- gpt-oss-120b: 20.0 (#245)
- Kimi K2.6: 40.5 (#55)

| Benchmark | gpt-oss-120b | Kimi K2.6 |
|---|---|---|
| CritPt | 1.1% | 8% |
| Chess Puzzles | 20% | 26% |
| LMArena Hard Prompts | 1364 | 1470 |
| Mystery Game Puzzles | 2% | 18% |
| DTBench | 76.3% | 90.9% |
| LMCA | 22.1% | 37.3% |
| Epoch Capabilities Index | 139.93 | 151.05 |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| NYT Connections (extended) | — | 87.2% |
| EBR-Bench | — | 2.4% |
| Surface Evolver Bench | 25% | — |

## Math

- gpt-oss-120b: 52.5 (#50)
- Kimi K2.6: 57.0 (#41)

| Benchmark | gpt-oss-120b | Kimi K2.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 96.1% |
| LMArena Math | 1389 | 1475 |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| ProofBench | — | 16% |
| Omni-MATH | 68.8% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |

## Knowledge

- gpt-oss-120b: 42.4 (#96)
- Kimi K2.6: 54.0 (#54)

| Benchmark | gpt-oss-120b | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 75.8% | 90.8% |
| Vectara Hallucination Rate | 14.2% | 10.8% |
| LMArena Expert | 1356 | 1491 |
| SimpleQA Verified | — | 34.9% |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| GPQA (HELM) | 68.4% | — |

## Multimodal

- gpt-oss-120b: —
- Kimi K2.6: 31.6 (#103)

| Benchmark | gpt-oss-120b | Kimi K2.6 |
|---|---|---|
| LMArena Vision | — | 1283 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |

## Multilingual

- gpt-oss-120b: 48.0 (#147)
- Kimi K2.6: 54.9 (#37)

| Benchmark | gpt-oss-120b | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1351 | 1446 |
| LMArena Chinese | 1385 | 1521 |
| LMArena French | 1369 | 1471 |
| LMArena German | 1353 | 1450 |
| LMArena Japanese | 1331 | 1443 |
| LMArena Korean | 1282 | 1427 |
| LMArena Russian | 1343 | 1446 |
| LMArena Spanish | 1389 | 1464 |

## Instruction Following

- gpt-oss-120b: 69.3 (#173)
- Kimi K2.6: 76.3 (#43)

| Benchmark | gpt-oss-120b | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1318 | 1451 |
| IFEval | 83.6% | — |

## Long Context

- gpt-oss-120b: 31.4 (#278)
- Kimi K2.6: 44.9 (#52)

| Benchmark | gpt-oss-120b | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1319 | 1468 |
| Fiction.LiveBench | 44.4% | — |

## Writing & Preference

- gpt-oss-120b: 46.5 (#217)
- Kimi K2.6: 68.5 (#26)

| Benchmark | gpt-oss-120b | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1365 | 1455 |
| LMArena Creative Writing | 1275 | 1434 |
| EQ-Bench Creative Writing | 961 | 1725 |
| LMArena Multi-Turn | 1340 | 1453 |
| Short-Story Creative Writing | 77.1% | — |
| WildBench | 84.5% | — |
| EQ-Bench 4 | — | 1202 |

## FAQ

### Is gpt-oss-120b better than Kimi K2.6?

Kimi K2.6 is the stronger model overall, scoring 47.7 to 36.3 on the Noometry Index. gpt-oss-120b costs 24× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.

### Which is cheaper, gpt-oss-120b or Kimi K2.6?

gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Kimi K2.6 lists at $0.95 and $4.

### Is gpt-oss-120b or Kimi K2.6 better for coding?

Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

Kimi K2.6 does, with 262K tokens against 131K.

### How many benchmarks do gpt-oss-120b and Kimi K2.6 share?

31 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Kimi K2.6 has 51.