Claude 3.5 Sonnetvsgpt-oss-120b
Claude 3.5 Sonnet | gpt-oss-120b | |
|---|---|---|
| Specifications | ||
Parameters | — | 117B |
Context window | — | 128k |
| 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. | 45%Best | 11% |
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. | 33.4% | 62.4%Best |
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% |
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. | 59.4% | 80.1%Best |
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% |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Jun 20 2024 | Aug 5 2025 |
| Access | Proprietary | Open Weight |
Which is better: Claude 3.5 Sonnet or gpt-oss-120b?
gpt-oss-120b leads Claude 3.5 Sonnet on 2 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, GPQA Diamond). Claude 3.5 Sonnet shipped 411 days before gpt-oss-120b, so benchmark comparisons should account for the intervening progress.
Claude 3.5 Sonnet is proprietary, while gpt-oss-120b is open weight.
On BullshitBench v2, Claude 3.5 Sonnet leads at 45% vs gpt-oss-120b at 11%. On SWE-Bench Verified, gpt-oss-120b leads at 62.4% vs Claude 3.5 Sonnet at 33.4%. On GPQA Diamond, gpt-oss-120b leads at 80.1% vs Claude 3.5 Sonnet at 59.4%.
Frequently asked questions
Claude 3.5 Sonnet was released by Anthropic on Jun 20 2024.
gpt-oss-120b was released by OpenAI on Aug 5 2025.
gpt-oss-120b leads on SWE-Bench Verified — Claude 3.5 Sonnet 33.4% vs gpt-oss-120b 62.4%.
gpt-oss-120b leads on GPQA Diamond — Claude 3.5 Sonnet 59.4% vs gpt-oss-120b 80.1%.
Claude 3.5 Sonnet is a proprietary model released by Anthropic. gpt-oss-120b is an open weight model released by OpenAI.