Claude Sonnet 5vsgpt-oss-20b
Claude Sonnet 5 | gpt-oss-20b | |
|---|---|---|
| Specifications | ||
Parameters | — | 21B |
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. | 80% | — |
Prompt injection robustness Gray Swan IPI · k = 1Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better. | 0.6% | — |
Prompt injection robustness Gray Swan IPI · k = 10Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 10 tries and counts an attack as successful if any of them works. Lower is better. | 4.7% | — |
Prompt injection robustness Gray Swan IPI · k = 15Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 15 tries and counts an attack as successful if any of them works. Lower is better. | 5.9% | — |
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. | 63.2% | — |
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. | — | 60.7% |
Agentic coding CursorBench v3.2Cursor's own test of harder, real-world coding tasks inside a code editor, on the refreshed v3.2 task set. Scores aren't comparable with v3.1. Higher is better. | 61.5% | — |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | 61.2% | — |
Next.js coding Next.js EvalsVercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | 79% | — |
Supabase coding Supabase Evals · with skillsSupabase's own open benchmark: a coding agent is dropped into a real Supabase project and asked to do real work — set up a schema, fix a broken security policy, debug an Edge Function — and every run is checked against a live Supabase stack. This is the headline number, where the agent has Supabase's own skills loaded, as most people building on Supabase would. The score is the share of scenarios it got right. Higher is better. | 95.5% | — |
Supabase coding Supabase Evals · no skillsThe same Supabase scenarios, but with none of Supabase's skills loaded — so it measures what the model already knows about building on Supabase, rather than how well it follows Supabase's supplied instructions. Higher is better. | 90.9% | — |
Agentic computer work Frontier-Bench v0.1A hard, ever-evolving set of real computer tasks — coding, system administration, data work, and more — that an AI agent has to complete on its own. Run by the Harbor / Laude Institute team as the successor to Terminal-Bench (v0.1 is the first release of the task set). The score is the share of tasks solved. Higher is better. | 14.6% | — |
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. | 80.4% | — |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | 84.7% | — |
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. | 43.2%Best | 10.9% |
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. | 57.4%Best | 17.3% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 71.5% |
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. | — | 85.3% |
Agentic computer use OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 81.2% | — |
Knowledge work GDPval-AAMeasures how well the AI does economically valuable knowledge work, judged against human experts. Shown as a rating (like a chess Elo) — higher is better. | 1618 | — |
Community preference Arena Elo (Text)Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | 1463 | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | 1543 | — |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Jun 30 2026 | Aug 5 2025 |
| Access | Proprietary | Open Weight |
Which is better: Claude Sonnet 5 or gpt-oss-20b?
Claude Sonnet 5 leads gpt-oss-20b on 2 of the 2 benchmarks they both report (Humanity's Last Exam). gpt-oss-20b shipped 329 days before Claude Sonnet 5, so benchmark comparisons should account for the intervening progress.
Claude Sonnet 5 is proprietary, while gpt-oss-20b is open weight.
On Humanity's Last Exam · no tools, Claude Sonnet 5 leads at 43.2% vs gpt-oss-20b at 10.9%. On Humanity's Last Exam · with tools, Claude Sonnet 5 leads at 57.4% vs gpt-oss-20b at 17.3%.
Frequently asked questions
Claude Sonnet 5 was released by Anthropic on Jun 30 2026.
gpt-oss-20b was released by OpenAI on Aug 5 2025.
Claude Sonnet 5 leads on Humanity's Last Exam · no tools — Claude Sonnet 5 43.2% vs gpt-oss-20b 10.9%.
Claude Sonnet 5 is a proprietary model released by Anthropic. gpt-oss-20b is an open weight model released by OpenAI.
Other comparisons
Claude Sonnet 5vsGemini 3.7 Flashgpt-oss-20bvsGemini 3.7 FlashClaude Sonnet 5vsMuse Glimmergpt-oss-20bvsMuse GlimmerClaude Sonnet 5vsGrok 4.6gpt-oss-20bvsGrok 4.6Claude Sonnet 5vsDeepSeek-V4-Pro-0813gpt-oss-20bvsDeepSeek-V4-Pro-0813Claude Sonnet 5vsMistral Medium 3.5gpt-oss-20bvsMistral Medium 3.5Claude Sonnet 5vsKimi K3gpt-oss-20bvsKimi K3