Benchmark Almanac

Last Secure Code Benchmark

Claude Fable 5 25.1% leads since October 2026
Qwen4-Max 31.8% leads since November 2026
In use

The official leaderboard hasn’t scored a model released after GLM-5.3 (August 2026). Labs report their own numbers for one newer model: Qwen4-Max at 31.8%.

Agents rebuild code that a real vulnerability once affected, from a specification that never mentions security. Hidden tests check function and replay an exploit.

450 tasks from 150 vulnerability scenarios, 115 from real CVEs and 35 expert written. Seven languages and 24 CWE classes. Each scenario appears at function, file and repository level. The headline metric counts a task only when both the function and security suites pass. Apache 2.0, also on Harbor Hub and Docker Hub.

Released
October 2026
Kind
Secure code and review
Level
Expert
Scored
Checked automatically
Answers
Code
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Code, Actions
Interaction
Agentic
Environment
Terminal
Refresh
One fixed set
Run by
Anyone
In views
Agents
Strongest model tested
Claude Fable 5 #12 on the capability index
Last in a launch post
November 2026
Last model added
November 2026
Scores refreshed
November 19th, 2026

In the authors’ words

AI coding agents now write much of the code that ships, yet whether that code is secure remains unclear. We introduce the Last Secure Code Benchmark, a comprehensive evaluation of secure code generation by coding agents. Built from 150 real vulnerabilities, its 450 tasks span seven widely used languages (Java, C, C++, JavaScript, Python, PHP, and Go), 24 CWEs including 21 of the 2025 CWE Top 25 and 8 of the Top 10 KEV weaknesses, more than any benchmark we compare with, and three vibe-coding scenarios: filling in a function, writing a file, and building a repository's source tree from scratch. Every task asks only for functionality, through a specification that never mentions security, and hidden functional and security tests grade the result. Across six frontier agents, 73.6% to 91.3% of tasks pass functionally, yet even the strongest, Claude Fable 5, produces code that is both functional and secure for only 25.1% of tasks, and the others for 16.4% to 24.7%. The best model only passes 12% of the vulnerability scenarios across all vibe coding setting, posing strong concern on the security of the code written by vibe coding.

Abstract of Last Secure Code Benchmark: Is the Code You Vibe Secure? (arXiv:2610.14766, CC0)
6
Models scored on its own leaderboard
1
Launch post lists it, from 1 lab

Claude Fable 5 leads with 25.1% among models released by August 2026

Best score per model from the benchmark's own leaderboard, read on November 19th, 2026. Where a model ran with several settings or harnesses, we keep its best.

Qwen4-Max leads with 31.8%, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.

The newest model with a score here came out in August 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Claude Fable 5 25.1%
  2. 2 GPT-5.6 Sol 24.7%
  3. 3 Qwen 3.8 Max 22%
  4. 4 GLM-5.3 21.3%
  5. 5 DeepSeek-V4-Pro 18%
  6. 6 Kimi K3 16.4%

Source: Official Last Secure Code Benchmark leaderboard

Sources: Labs’ model cards and official Last Secure Code Benchmark leaderboard

#ModelScoreSettingDateSource
1 Claude Fable 5 25.1% Claude Code Jun 2026 Official leaderboard
2 GPT-5.6 Sol 24.7% Codex Jul 2026 Official leaderboard
3 Qwen 3.8 Max 22% Claude Code Aug 2026 Official leaderboard
4 GLM-5.3 21.3% Claude Code Aug 2026 Official leaderboard
5 DeepSeek-V4-Pro 18% Claude Code Apr 2026 Official leaderboard
6 Kimi K3 16.4% Claude Code Jul 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Qwen4-Max 31.8% Nov 2026 Lab model card
2 Claude Fable 5 25.1% Claude Code Jun 2026 Official leaderboard
3 GPT-5.6 Sol 24.7% Codex Jul 2026 Official leaderboard
4 Qwen 3.8 Max 22% Claude Code Aug 2026 Official leaderboard
5 GLM-5.3 21.3% Claude Code Aug 2026 Official leaderboard
6 DeepSeek-V4-Pro 18% Claude Code Apr 2026 Official leaderboard
7 Kimi K3 16.4% Claude Code Jul 2026 Official leaderboard

Labs report scores for 1 model in their cards. Switch the scores above to rank them together.

Number one over time 2 models have held number one with claims included since its release in October 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic
Own leaderboard Not tested since Oct 2026

Source: Official Last Secure Code Benchmark leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Qwen4-Max Claude Fable 5 DeepSeek-V4-Pro 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Qwen4-Max Claude Fable 5

Sources: Official Last Secure Code Benchmark leaderboard and labs’ model cards

One lab put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Qwen
DateLaunch postScoreAs the post writes it
Nov 15, 2026 Qwen4-Max 31.8 Last Secure Code Bench, code reconstruction without a security hint, function-level pass rate for both function and security

Versions

More in Cybersecurity

All 138 in Cybersecurity
  • ExploitGym In use 869 real-vulnerability exploit-development tasks (userspace, V8, Linux kernel). Success means capturing a flag through the intended vulnerability. GPT-6 Astra 42.4%
  • ExploitBench In use 41 recent V8 JavaScript-engine N-day vulnerabilities. Progress measured by 16 grader-verified capability flags across five tiers. GPT-6 Astra 100%
  • ExploitBench - Internal Port In use Agents develop working exploits for recently disclosed vulnerabilities to limit contamination. Scored as arbitrary code execution success rate. GPT-6.2 Astra 53.5%
  • Atomic Challenges In use Agents solve 22 skill-level offensive security challenges in vulnerability research, network attack simulation and evasion. Scored as challenges solved. GPT-6 Astra 90.9%
  • MiMo Cyber Bench In use Agents do in-house cybersecurity tasks that add to public vulnerability reproduction and exploitation benchmarks. The report gives no task count or grading details. MiMo-V2.6 Pro 81.7%
  • PatchBench (OpenAI) In use Models patch security flaws. Automated tests and model-based review check that each patch fixes the flaw, keeps the intended behavior and is ready to merge. GPT-6.2 Astra 79.7%

Data audit

All 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (6 entries) and launch posts (1 score).
  • Pass Models scored 7 models we track.
  • Pass Newest score The newest is from November 2026, for Qwen4-Max.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Fable 5 (#12).
  • Pass Headroom The best is 31.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on last-secure-code-benchmark.github.io: 6 rows for models we track at the last read.
  • Pass Last read November 19th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check