Model comparison
gpt-oss-120b vs Kimi K2.5
Kimi K2.5 is the stronger model overall, scoring 48.1 to 36.3 on the Noometry Index. gpt-oss-120b costs 13× less per token, which makes it the better buy when Kimi K2.5's lead doesn't matter for your workload.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. gpt-oss-120b scores higher in 1 category and Kimi K2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Kimi K2.5 leads 34.2 to 12.2.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 26% for gpt-oss-120b and 70.8% for Kimi K2.5.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.45 / $2.25 for Kimi K2.5.
- Kimi K2.5 accepts more context: 262K tokens versus 131K.
Side by side
| gpt-oss-120b | Kimi K2.5 | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 36.3 | 48.1 |
| Released | 2025-08-05 | 2026-01-27 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 41K | 262K |
| Input $ / M tokens | $0.037 | $0.45 |
| Output $ / M tokens | $0.17 | $2.25 |
| Results tracked | 48 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
gpt-oss-120b: 33.5 (#256), Kimi K2.5: 48.8 (#53)
| Benchmark | gpt-oss-120b | Kimi K2.5 |
|---|---|---|
| SWE-bench Verified (bash only) | 26% | 70.8% |
| SciCode | 36% | 49% |
| WeirdML | 48.2% | 45.6% |
| LMArena Coding | 1380 | 1474 |
| ALE-Bench | 575.62 | 821.65 |
| SWE-bench Verified | — | 73.8% |
| Aider Polyglot | 41.8% | — |
| LMArena WebDev | — | 1437 |
| SWE-bench Multilingual | — | 67.3% |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Kimi K2.5 leads
gpt-oss-120b: 12.2 (#153), Kimi K2.5: 34.2 (#48)
| Benchmark | gpt-oss-120b | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | 18.7% | 43.2% |
| Vending-Bench 2 | -21.53 | 1,198 |
| APEX-Agents | 4.4% | — |
| OSWorld | — | 63.3% |
| METR Time Horizons | 56.6% | — |
Reasoning Kimi K2.5 leads
gpt-oss-120b: 20.0 (#245), Kimi K2.5: 31.2 (#80)
| Benchmark | gpt-oss-120b | Kimi K2.5 |
|---|---|---|
| SimpleBench | 22.1% | 46.8% |
| Kagi LLM Benchmark | 58.6% | 78.5% |
| CritPt | 1.1% | 3.1% |
| Chess Puzzles | 20% | 12% |
| LMArena Hard Prompts | 1364 | 1453 |
| Epoch Capabilities Index | 139.93 | 148.03 |
| ARC-AGI-2 | — | 11.8% |
| NYT Connections (extended) | — | 69.9% |
| ARC-AGI-1 | — | 65.3% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
Math Too close to call
gpt-oss-120b: 52.5 (#50), Kimi K2.5: 51.8 (#53)
| Benchmark | gpt-oss-120b | Kimi K2.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 92.2% |
| LMArena Math | 1389 | 1470 |
| MathArena Final-Answer Competitions | — | 62.3% |
| Omni-MATH | 68.8% | — |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Kimi K2.5 leads
gpt-oss-120b: 42.4 (#96), Kimi K2.5: 53.6 (#56)
| Benchmark | gpt-oss-120b | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 75.8% | 87.6% |
| Vectara Hallucination Rate | 14.2% | 14.2% |
| LMArena Expert | 1356 | 1466 |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| GPQA (HELM) | 68.4% | — |
Multimodal Not comparable
gpt-oss-120b: —, Kimi K2.5: 41.1 (#39)
| Benchmark | gpt-oss-120b | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |
Multilingual Kimi K2.5 leads
gpt-oss-120b: 48.0 (#147), Kimi K2.5: 53.9 (#53)
| Benchmark | gpt-oss-120b | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1351 | 1433 |
| LMArena Chinese | 1385 | 1495 |
| LMArena French | 1369 | 1454 |
| LMArena German | 1353 | 1441 |
| LMArena Japanese | 1331 | 1421 |
| LMArena Korean | 1282 | 1410 |
| LMArena Russian | 1343 | 1435 |
| LMArena Spanish | 1389 | 1450 |
Instruction Following Kimi K2.5 leads
gpt-oss-120b: 69.3 (#173), Kimi K2.5: 75.3 (#64)
| Benchmark | gpt-oss-120b | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1318 | 1431 |
| IFEval | 83.6% | — |
Long Context Kimi K2.5 leads
gpt-oss-120b: 31.4 (#278), Kimi K2.5: 52.1 (#7)
| Benchmark | gpt-oss-120b | Kimi K2.5 |
|---|---|---|
| Fiction.LiveBench | 44.4% | 86.1% |
| LMArena Longer Query | 1319 | 1445 |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference Kimi K2.5 leads
gpt-oss-120b: 46.5 (#217), Kimi K2.5: 65.1 (#53)
| Benchmark | gpt-oss-120b | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1365 | 1445 |
| LMArena Creative Writing | 1275 | 1423 |
| EQ-Bench Creative Writing | 961 | 1579 |
| LMArena Multi-Turn | 1340 | 1444 |
| Short-Story Creative Writing | 77.1% | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Kimi K2.5?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 36.3 on the Noometry Index. gpt-oss-120b costs 13× less per token, which makes it the better buy when Kimi K2.5's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-120b or Kimi K2.5?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Kimi K2.5 lists at $0.45 and $2.25.
Is gpt-oss-120b or Kimi K2.5 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.5 does, with 262K tokens against 131K.
How many benchmarks do gpt-oss-120b and Kimi K2.5 share?
33 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Kimi K2.5 has 51.