Model comparison
gpt-oss-120b vs Kimi K2.7 Code
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 36.3 on the Noometry Index. gpt-oss-120b costs 24× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. gpt-oss-120b scores higher in 0 categories and Kimi K2.7 Code in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.7 Code leads 39.0 to 20.0.
- The biggest single-benchmark swing is SimpleBench: 22.1% for gpt-oss-120b and 57.9% for Kimi K2.7 Code.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
- Kimi K2.7 Code accepts more context: 262K tokens versus 131K.
Side by side
| gpt-oss-120b | Kimi K2.7 Code | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 36.3 | 43.3 |
| Released | 2025-08-05 | 2026-06-12 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 41K | 262K |
| Input $ / M tokens | $0.037 | $0.95 |
| Output $ / M tokens | $0.17 | $4 |
| Results tracked | 48 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.7 Code leads
gpt-oss-120b: 33.5 (#256), Kimi K2.7 Code: 42.9 (#95)
| Benchmark | gpt-oss-120b | Kimi K2.7 Code |
|---|---|---|
| SciCode | 36% | 47.5% |
| WeirdML | 48.2% | 54.1% |
| ALE-Bench | 575.62 | 886.23 |
| DeepSWE | — | 30.5% |
| FrontierCode | — | 30.1% |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| LMArena WebDev | — | 1473 |
| LMArena Coding | 1380 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Kimi K2.7 Code leads
gpt-oss-120b: 12.2 (#153), Kimi K2.7 Code: 24.0 (#122)
| Benchmark | gpt-oss-120b | Kimi K2.7 Code |
|---|---|---|
| APEX-Agents | 4.4% | 37.6% |
| Vending-Bench 2 | -21.53 | 5,083 |
| Terminal-Bench | 18.7% | — |
| GBAEval | — | 0.9% |
| METR Time Horizons | 56.6% | — |
Reasoning Kimi K2.7 Code leads
gpt-oss-120b: 20.0 (#245), Kimi K2.7 Code: 39.0 (#61)
| Benchmark | gpt-oss-120b | Kimi K2.7 Code |
|---|---|---|
| SimpleBench | 22.1% | 57.9% |
| CritPt | 1.1% | 10% |
| Chess Puzzles | 20% | 21% |
| Surface Evolver Bench | 25% | 48.8% |
| Epoch Capabilities Index | 139.93 | 149.97 |
| Kagi LLM Benchmark | 58.6% | — |
| LMArena Hard Prompts | 1364 | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
Math Too close to call
gpt-oss-120b: 52.5 (#50), Kimi K2.7 Code: 52.9 (#48)
| Benchmark | gpt-oss-120b | Kimi K2.7 Code |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 95.6% |
| FrontierMath (Tiers 1-3) | — | 54% |
| FrontierMath Tier 4 | — | 12.2% |
| Omni-MATH | 68.8% | — |
| LMArena Math | 1389 | — |
Knowledge Kimi K2.7 Code leads
gpt-oss-120b: 42.4 (#96), Kimi K2.7 Code: 53.5 (#57)
| Benchmark | gpt-oss-120b | Kimi K2.7 Code |
|---|---|---|
| GPQA Diamond | 75.8% | 87.9% |
| SimpleQA Verified | — | 36.5% |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
| LMArena Expert | 1356 | — |
Multilingual Not comparable
gpt-oss-120b: 48.0 (#147), Kimi K2.7 Code: —
| Benchmark | gpt-oss-120b | Kimi K2.7 Code |
|---|---|---|
| LMArena Non-English | 1351 | — |
| LMArena Chinese | 1385 | — |
| LMArena French | 1369 | — |
| LMArena German | 1353 | — |
| LMArena Japanese | 1331 | — |
| LMArena Korean | 1282 | — |
| LMArena Russian | 1343 | — |
| LMArena Spanish | 1389 | — |
Instruction Following Not comparable
gpt-oss-120b: 69.3 (#173), Kimi K2.7 Code: —
| Benchmark | gpt-oss-120b | Kimi K2.7 Code |
|---|---|---|
| IFEval | 83.6% | — |
| LMArena Instruction Following | 1318 | — |
Long Context Not comparable
gpt-oss-120b: 31.4 (#278), Kimi K2.7 Code: —
| Benchmark | gpt-oss-120b | Kimi K2.7 Code |
|---|---|---|
| Fiction.LiveBench | 44.4% | — |
| LMArena Longer Query | 1319 | — |
Writing & Preference Not comparable
gpt-oss-120b: 46.5 (#217), Kimi K2.7 Code: —
| Benchmark | gpt-oss-120b | Kimi K2.7 Code |
|---|---|---|
| LMArena Text | 1365 | — |
| LMArena Creative Writing | 1275 | — |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
| LMArena Multi-Turn | 1340 | — |
Frequently asked questions
Is gpt-oss-120b better than Kimi K2.7 Code?
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 36.3 on the Noometry Index. gpt-oss-120b costs 24× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-120b or Kimi K2.7 Code?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.
Is gpt-oss-120b or Kimi K2.7 Code better for coding?
Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.7 Code does, with 262K tokens against 131K.
How many benchmarks do gpt-oss-120b and Kimi K2.7 Code share?
12 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Kimi K2.7 Code has 19.