gpt-oss-120b vs Kimi K3
gpt-oss-120b (OpenAI) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.
- Kimi K3 leads on overall intelligence (ECI 158 vs 140).
- gpt-oss-120b is cheaper on input tokens — $0.03 vs $2.10 per 1M.
- Kimi K3 has a larger context window (1M vs 131K tokens).
- Kimi K3 ranks higher for coding (97th vs 36th percentile).
| Attribute | gpt-oss-120b | Kimi K3 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 140 | 158 |
| Coding | 36 | 97 |
| Math | 43 | 82 |
| Reasoning & Knowledge | 17 | 73 |
| Agentic & Tools | 8 | 80 |
| Specifications | ||
| Developer | OpenAI | Moonshot |
| Family | GPT | Kimi |
| Released | Aug 5, 2025 | Jul 16, 2026 |
| Parameters | 116.8B | 2.8T |
| Availability | Open weights (unrestricted) | Open weights (non-commercial) |
| Context window | 131K | 1M |
| Price — $/M input | $0.03 | $2.10 |
| Price — $/M output | $0.17 | $10.95 |
| Inputs | text | text, image, video |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 89% | 97% |
| APEX | 5% | 39% |
| GPQA Diamond | 76% | 93% |
| Humanity's Last Exam | 20% | 47% |
| LiveCodeBench | 88% | — |
| METR task horizon | 42 min | — |
| MMLU-Pro | 81% | — |
| SciCode | 34% | 60% |
| SimpleBench | 22% | 61% |
| SimpleQA Verified | 14% | 51% |
| Terminal-Bench | 19% | — |
| WeirdML | 48% | 83% |
| τ²-bench | 66% | — |
| ARC-AGI | — | 95% |
| ARC-AGI-2 | — | 60% |
| WebDev Arena | — | 1674 |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Is gpt-oss-120b better than Kimi K3?
On Epoch AI's Capabilities Index, Kimi K3 scores higher (158) than gpt-oss-120b (140). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, gpt-oss-120b or Kimi K3?
gpt-oss-120b is cheaper on input tokens at $0.03 per million, versus $2.10 (representative OpenRouter pricing).
Which has a larger context window, gpt-oss-120b or Kimi K3?
Kimi K3 supports up to 1M tokens, compared with 131K for the other.
Which is better for coding, gpt-oss-120b or Kimi K3?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 97th vs 36th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.