gpt-oss-120bvsQwen3.8-27B
gpt-oss-120b | Qwen3.8-27B | |
|---|---|---|
| Specifications | ||
Parameters | 117B | 27B |
Context window | 128k | 262k |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 11% | — |
Agentic coding SWE-Bench ProCan the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | — | 61.7% |
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 62.4% | — |
Agentic coding DeepSWE 1.1Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | — | 42.2% |
Repo-level code generation NL2Repo-BenchTests whether the AI can turn a natural-language requirement into working code across an entire repository, not just produce a single function or patch. Higher is better. | — | 42.3% |
Software engineering QwenSWEBenchQwen's in-house coding benchmark for evaluating a model's ability to complete software-engineering work. Higher is better. | — | 79% |
Competitive coding LiveCodeBenchCoding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | — | 90.3% |
Agentic terminal coding Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 73% |
Professional tool use JobBenchTests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | — | 33.4% |
Long-horizon office work CoWorkBenchTests long-running office tasks across fields including computer science, finance, law, medicine, and other productivity work. Higher is better. | — | 70.7% |
Multidisciplinary reasoning Humanity's Last Exam · no toolsHumanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | 14.9% | 30.8%Best |
Multidisciplinary reasoning Humanity's Last Exam · with toolsHumanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | 19% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 80.1% | 89.2%Best |
Instruction following IFBenchTests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 79.5% |
General knowledge MMLUA 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 90% | — |
Agentic computer use Agent's Last Exam · pass@1A hard set of desktop and operating-system tasks an AI agent has to finish by looking at the screen and working the machine itself. The score is the share it passes outright — partial credit does not count. Higher is better. | — | 20.4% |
Agentic computer use Agent's Last Exam · scoreThe graded score on the same desktop and operating-system tasks in Agent's Last Exam, giving partial credit for progress beyond the strict pass-or-fail result. Higher is better. | — | 42.9% |
| Overview | ||
| Company | OpenAI | Qwen |
| Release date | Aug 5 2025 | Aug 14 2026 |
| Access | Open Weight | Open Weight |
Which is better: gpt-oss-120b or Qwen3.8-27B?
Qwen3.8-27B leads gpt-oss-120b on 2 of the 2 benchmarks they both report (Humanity's Last Exam, GPQA Diamond). gpt-oss-120b shipped 374 days before Qwen3.8-27B, so benchmark comparisons should account for the intervening progress.
gpt-oss-120b has 117B parameters, while Qwen3.8-27B has 27B. Context windows are 128k (gpt-oss-120b) vs 262k (Qwen3.8-27B).
On Humanity's Last Exam · no tools, Qwen3.8-27B leads at 30.8% vs gpt-oss-120b at 14.9%. On GPQA Diamond, Qwen3.8-27B leads at 89.2% vs gpt-oss-120b at 80.1%.
Frequently asked questions
gpt-oss-120b was released by OpenAI on Aug 5 2025.
Qwen3.8-27B was released by Qwen on Aug 14 2026.
Qwen3.8-27B leads on Humanity's Last Exam · no tools — gpt-oss-120b 14.9% vs Qwen3.8-27B 30.8%.
gpt-oss-120b has a 128k context window; Qwen3.8-27B has 262k.
Other comparisons
gpt-oss-120bvsClaude Opus 5Qwen3.8-27BvsClaude Opus 5gpt-oss-120bvsGemini 3.7 FlashQwen3.8-27BvsGemini 3.7 Flashgpt-oss-120bvsMuse GlimmerQwen3.8-27BvsMuse Glimmergpt-oss-120bvsGrok 4.6Qwen3.8-27BvsGrok 4.6gpt-oss-120bvsDeepSeek-V4-Pro-0813Qwen3.8-27BvsDeepSeek-V4-Pro-0813gpt-oss-120bvsMistral Medium 3.5Qwen3.8-27BvsMistral Medium 3.5