Benchmark Almanac

WebExploitBench

GPT-5.5 36.4% leads since June 2026
Gemini 4 Neon 51.3% leads since November 2026
In use

The benchmark’s paper hasn’t scored a model released after Qwen3.7-Max (May 2026). Labs report their own numbers for one newer model: Gemini 4 Neon at 51.3%.

Agents find and exploit 110 vulnerabilities in 15 real web applications, each in its own container. A verifier checks that the agent's proof of concept hits the same endpoint as the reference exploit.

The vulnerabilities are 18 zero-day, 56 one-day and 36 synthetic, across 17 kinds such as SQL injection and SSRF. The repo holds 5 of the 15 apps, and the full set is on Hugging Face behind a gate, for evaluation only. Google reports version 1.2.

Made by
AgentCyberRange
Released
June 2026
Kind
Finding and exploiting real bugs
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Code, Actions
Interaction
Agentic
Environment
Terminal, Browser
Run by
Anyone
Strongest model tested
GPT-5.5 #21 on the capability index
Last in a launch post
November 2026
Last model added
November 2026
Scores refreshed
November 20th, 2026
6
Models scored in its paper
1
Launch post lists it, from 1 lab
1
System card reports it, from 1 lab

GPT-5.5 leads with 36.4% among models released by May 2026

Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.

Gemini 4 Neon leads with 51.3%, 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 May 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 GPT-5.5 Level 1, xhigh 36.4%
  2. 2 Claude Opus 4.7 Level 2, max 29.1%
  3. 3 Qwen3.7-Max Level 1 26.4%
  4. 4 GLM-5.1 Level 2 17.3%
  5. 5 DeepSeek-V4-Pro Level 2 13.6%
  6. 6 Kimi K2.6 Level 1 12.7%

Source: The WebExploitBench paper

#ModelScoreSettingDateSource
1 GPT-5.5 36.4% Level 1, xhigh, Codex 0.133.0 Apr 2026 Official leaderboard
2 Claude Opus 4.7 29.1% Level 2, max, Claude Code 2.1.150 Apr 2026 Official leaderboard
3 Qwen3.7-Max 26.4% Level 1, Qwen Code 0.16.1 May 2026 Official leaderboard
4 GLM-5.1 17.3% Level 2, Claude Code 2.1.150 Apr 2026 Official leaderboard
5 DeepSeek-V4-Pro 13.6% Level 2, Claude Code 2.1.150 Apr 2026 Official leaderboard
6 Kimi K2.6 12.7% Level 1, Kimi Code 1.44.0 Apr 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 4 Neon 51.3% Nov 2026 Lab model card
2 GPT-5.5 36.4% Level 1, xhigh, Codex 0.133.0 Apr 2026 Official leaderboard
3 Claude Opus 4.7 29.1% Level 2, max, Claude Code 2.1.150 Apr 2026 Official leaderboard
4 Qwen3.7-Max 26.4% Level 1, Qwen Code 0.16.1 May 2026 Official leaderboard
5 GLM-5.1 17.3% Level 2, Claude Code 2.1.150 Apr 2026 Official leaderboard
6 DeepSeek-V4-Pro 13.6% Level 2, Claude Code 2.1.150 Apr 2026 Official leaderboard
7 Kimi K2.6 12.7% Level 1, Kimi Code 1.44.0 Apr 2026 Official leaderboard

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

More effort adds a median 17 points

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
GPT-5.5 Codex 0.133.0
Level 0, xh… Level 2, xh… Level 1, xh…
36.4%
Claude Opus 4.7 Claude Code 2.1.150
Level 0, max Level 1, max Level 2, max
29.1%
Qwen3.7-Max Qwen Code 0.16.1
Level 0 Level 1
26.4%
GLM-5.1 Claude Code 2.1.150
Level 0 Level 2
17.3%
DeepSeek-V4-Pro Claude Code 2.1.150
Level 0 Level 2
13.6%
Kimi K2.6 Kimi Code 1.44.0
Level 0 Level 2 Level 1
12.7%

Source: The WebExploitBench paper

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-5.5 Level 1, xhigh Codex 0.133.0 36.4%
GPT-5.5 Level 2, xhigh Codex 0.133.0 31.8%
Claude Opus 4.7 Level 2, max Claude Code 2.1.150 29.1%
Qwen3.7-Max Level 1 Qwen Code 0.16.1 26.4%
Claude Opus 4.7 Level 1, max Claude Code 2.1.150 24.6%
GPT-5.5 Level 0, xhigh Codex 0.133.0 19.1%
GLM-5.1 Level 2 Claude Code 2.1.150 17.3%
Claude Opus 4.7 Level 0, max Claude Code 2.1.150 16.4%
DeepSeek-V4-Pro Level 2 Claude Code 2.1.150 13.6%
GLM-5.1 Level 1 Claude Code 2.1.150 12.7%
Kimi K2.6 Level 1 Kimi Code 1.44.0 12.7%
DeepSeek-V4-Pro Level 1 Claude Code 2.1.150 12.7%
Qwen3.7-Max Level 2 Qwen Code 0.16.1 12.7%
GLM-5.1 Level 0 Claude Code 2.1.150 11.8%
Qwen3.7-Max Level 0 Qwen Code 0.16.1 10.9%
DeepSeek-V4-Pro Level 0 Claude Code 2.1.150 10%
Kimi K2.6 Level 2 Kimi Code 1.44.0 9.09%
Kimi K2.6 Level 0 Kimi Code 1.44.0 3.64%

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

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

OpenAI
Benchmark paper Not tested since Jun 2026
GPT-5.5 36.4%

Source: The WebExploitBench paper

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
In the benchmark’s paper Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Gemini 4 Neon GPT-5.5 Claude Opus 4.7 GLM-5.1 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Gemini 4 Neon GPT-5.5

Sources: Official WebExploitBench 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.

Google DeepMind
DateLaunch postScoreAs the post writes it
Nov 18, 2026 Gemini 4 Neon 51.3 WebExploitBench v1.2 (51.26% in the text, 51.3% in the table)

One system card reports it

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
Nov 18, 2026 Gemini 4 Neon model card 51.3 WebExploitBench v1.2 (51.26% in the text, 51.3% in the table) (results table, p.4) Cyber risk

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

9 of 10 checks pass, 1 warning. Look first at the Confidence check. Likely. Some facts rest on secondary sources. Every benchmark

Catalog record 1 warning 1 pass
  • Pass Task access All tasks are public.
  • Warning Confidence Likely. Some facts rest on secondary sources.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (6 entries), launch posts (1 score) and system cards (1 score).
  • Pass Models scored 7 models we track.
  • Pass Newest score The newest is from November 2026, for Gemini 4 Neon.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 (#21).
  • Pass Headroom The best is 51.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 18 rows for models we track at the last read.
  • Pass Last read November 20th, 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