CWE-bench 2
Version 2
Agents audit and patch vulnerabilities in 250 codebases. The score is pass@1 under deterministic verification.
The board publishes pass@4 and average API cost per rollout. Runs use high reasoning and a one-hour task limit.
- Made by
- Collinear AI
- Released
- November 2026
- Kind
- Secure code and review
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Items from
- Real work and use
- Refresh
- New versions replace it
- Run by
- A host
- Based on
- CWE-bench
- In views
- Agents
- Strongest model tested
- GPT-6.2 Astra #1 on the capability index
- Last in a launch post
- November 2026
- Last model added
- November 2026
- Scores refreshed
- November 19th, 2026
Claude Fable 5.2 leads with 75%
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. Every run is in the next chart.
- 75.0 Claude Fable 5.2
- 70.7
Gemini 4 Neon
- 68.1
Gemini 4 Hydrogen
- 67.3
Gemini 4 Carbon
- 67.1 Claude Opus 5.5
- 66.8 GPT-6.2 Astra
- 66.1
Muse Wonder
- 66.0 GPT-6.2 Sol
- 65.0
Gemini 4 Argon
- 64.2 GPT-6 Astra
- 64.1
Tencent Hy4
- 61.4 Claude Sonnet 5.5
- 60.0 GPT-6.1 Terra
- 57.6
DeepSeek V4.1 Flash 1017
- 54.7 Grok 4.7
- 47.3
Tencent Hy4 preview
- 45.6
Mistral Large 4
- 45.4
Qwen3.8 Max (0902)
- 45.3 Kimi K3.1 Pro
- 42.0 GLM-5.3
- 1 Claude Fable 5.2 high reasoning; 1h limit 75%
- 2
Gemini 4 Neon high reasoning; 1h limit 70.7%
- 3
Gemini 4 Hydrogen high reasoning; 1h limit 68.1%
- 4
Gemini 4 Carbon high reasoning; 1h limit 67.3%
- 5 Claude Opus 5.5 high reasoning; 1h limit 67.1%
- 6 GPT-6.2 Astra high reasoning; 1h limit 66.8%
- 7
Muse Wonder high reasoning; 1h limit 66.1%
- 8 GPT-6.2 Sol high reasoning; 1h limit 66%
- 9
Gemini 4 Argon high reasoning; 1h limit 65%
- 10 GPT-6 Astra high reasoning; 1h limit 64.2%
- 11
Tencent Hy4 high reasoning; 1h limit 64.1%
- 12 Claude Sonnet 5.5 high reasoning; 1h limit 61.4%
- 13 GPT-6.1 Terra high reasoning; 1h limit 60%
- 14
DeepSeek V4.1 Flash 1017 high reasoning; 1h limit 57.6%
- 15 Grok 4.7 high reasoning; 1h limit 54.7%
- 16
Tencent Hy4 preview high reasoning; 1h limit 47.3%
- 17
Mistral Large 4 high reasoning; 1h limit 45.6%
- 18
Qwen3.8 Max (0902) high reasoning; 1h limit 45.4%
- 19 Kimi K3.1 Pro high reasoning; 1h limit 45.3%
- 20 GLM-5.3 high reasoning; 1h limit 42%
Source: Official CWE-bench 2 leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 75% | high reasoning; 1h limit, Claude Code | Nov 2026 | Official leaderboard |
| 2 | | 70.7% | high reasoning; 1h limit, Antigravity | Nov 2026 | Official leaderboard |
| 3 | | 68.1% | high reasoning; 1h limit, Antigravity | Nov 2026 | Official leaderboard |
| 4 | | 67.3% | high reasoning; 1h limit, Antigravity | Oct 2026 | Official leaderboard |
| 5 | Claude Opus 5.5 | 67.1% | high reasoning; 1h limit, Claude Code | Sep 2026 | Official leaderboard |
| 6 | GPT-6.2 Astra | 66.8% | high reasoning; 1h limit, Codex | Nov 2026 | Official leaderboard |
| 7 | | 66.1% | high reasoning; 1h limit, opencode | Oct 2026 | Official leaderboard |
| 8 | GPT-6.2 Sol | 66% | high reasoning; 1h limit, Codex | Nov 2026 | Official leaderboard |
| 9 | | 65% | high reasoning; 1h limit, Antigravity | Sep 2026 | Official leaderboard |
| 10 | GPT-6 Astra | 64.2% | high reasoning; 1h limit, Codex | Sep 2026 | Official leaderboard |
| 11 | | 64.1% | high reasoning; 1h limit, Claude Code | Nov 2026 | Official leaderboard |
| 12 | Claude Sonnet 5.5 | 61.4% | high reasoning; 1h limit, Claude Code | Sep 2026 | Official leaderboard |
| 13 | GPT-6.1 Terra | 60% | high reasoning; 1h limit, Codex | Oct 2026 | Official leaderboard |
| 14 | | 57.6% | high reasoning; 1h limit, opencode | Oct 2026 | Official leaderboard |
| 15 | Grok 4.7 | 54.7% | high reasoning; 1h limit, opencode | Sep 2026 | Official leaderboard |
| 16 | | 47.3% | high reasoning; 1h limit, opencode | Aug 2026 | Official leaderboard |
| 17 | | 45.6% | high reasoning; 1h limit, opencode | Oct 2026 | Official leaderboard |
| 18 | | 45.4% | high reasoning; 1h limit, opencode | Sep 2026 | Official leaderboard |
| 19 | Kimi K3.1 Pro | 45.3% | high reasoning; 1h limit, opencode | Oct 2026 | Official leaderboard |
| 20 | GLM-5.3 | 42% | high reasoning; 1h limit, opencode | Aug 2026 | Official leaderboard |
Labs report scores for 1 model in their cards. We plot every source in the charts below.
Pass@1 and average cost per rollout
The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Pass@1 | Mean cost per rollout |
|---|---|---|---|
| Claude Fable 5.2 | high reasoning; 1h limit, Claude Code | 75% | $7.85 |
| high reasoning; 1h limit, Antigravity | 70.7% | $6.52 | |
| high reasoning; 1h limit, Antigravity | 68.1% | $2.63 | |
| high reasoning; 1h limit, Antigravity | 67.3% | $4.27 | |
| Claude Opus 5.5 | high reasoning; 1h limit, Claude Code | 67.1% | $1.85 |
| GPT-6.2 Astra | high reasoning; 1h limit, Codex | 66.8% | $4.32 |
| high reasoning; 1h limit, opencode | 66.1% | $2.73 | |
| GPT-6.2 Sol | high reasoning; 1h limit, Codex | 66% | $0.81 |
| high reasoning; 1h limit, Antigravity | 65% | $3.7 | |
| GPT-6 Astra | high reasoning; 1h limit, Codex | 64.2% | $3.87 |
| high reasoning; 1h limit, Claude Code | 64.1% | $1.35 | |
| Claude Sonnet 5.5 | high reasoning; 1h limit, Claude Code | 61.4% | $0.58 |
| GPT-6.1 Terra | high reasoning; 1h limit, Codex | 60% | $0.44 |
| high reasoning; 1h limit, opencode | 57.6% | $0.04 | |
| Grok 4.7 | high reasoning; 1h limit, opencode | 54.7% | $2.97 |
| high reasoning; 1h limit, opencode | 47.3% | $0.43 | |
| high reasoning; 1h limit, opencode | 45.6% | $0.37 | |
| high reasoning; 1h limit, opencode | 45.4% | $2.06 | |
| Kimi K3.1 Pro | high reasoning; 1h limit, opencode | 45.3% | $0.96 |
| GLM-5.3 | high reasoning; 1h limit, opencode | 42% | $0.58 |
The best score, 75%, costs $7.85 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official CWE-bench 2 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.2 | high reasoning; 1h limit | Claude Code | 75% | $7.85 | |
| high reasoning; 1h limit | Antigravity | 70.7% | $6.52 | ||
| high reasoning; 1h limit | Antigravity | 68.1% | $2.63 | ||
| high reasoning; 1h limit | Antigravity | 67.3% | $4.27 | ||
| Claude Opus 5.5 | high reasoning; 1h limit | Claude Code | 67.1% | $1.85 | |
| GPT-6.2 Astra | high reasoning; 1h limit | Codex | 66.8% | $4.32 | |
| high reasoning; 1h limit | opencode | 66.1% | $2.73 | ||
| GPT-6.2 Sol | high reasoning; 1h limit | Codex | 66% | $0.81 | |
| high reasoning; 1h limit | Antigravity | 65% | $3.70 | ||
| GPT-6 Astra | high reasoning; 1h limit | Codex | 64.2% | $3.87 | |
| high reasoning; 1h limit | Claude Code | 64.1% | $1.35 | ||
| Claude Sonnet 5.5 | high reasoning; 1h limit | Claude Code | 61.4% | $0.58 | |
| GPT-6.1 Terra | high reasoning; 1h limit | Codex | 60% | $0.44 | |
| high reasoning; 1h limit | opencode | 57.6% | $0.04 | ||
| Grok 4.7 | high reasoning; 1h limit | opencode | 54.7% | $2.97 | |
| high reasoning; 1h limit | opencode | 47.3% | $0.43 | ||
| high reasoning; 1h limit | opencode | 45.6% | $0.37 | ||
| high reasoning; 1h limit | opencode | 45.4% | $2.06 | ||
| Kimi K3.1 Pro | high reasoning; 1h limit | opencode | 45.3% | $0.96 | |
| GLM-5.3 | high reasoning; 1h limit | opencode | 42% | $0.58 |
2 models have held number one on the official leaderboard since its release in November 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official CWE-bench 2 leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official CWE-bench 2 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.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Nov 18, 2026 | 70.7 | CWE-Bench v2 |
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.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 18, 2026 | | 70.7 | CWE-Bench v2 (results table, p.4) | Cyber risk |
One lab claim next to the leaderboard
Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| | 70.7% CWE-Bench v2 | 70.7% Leaderboard, high reasoning; 1h limit, Antigravity | Same |
Versions
We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.
Source: Official leaderboards
More 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 12 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (20 entries), launch posts (1 score) and system cards (1 score).
- Pass Models scored 20 models we track.
- Pass Newest score The newest is from November 2026, for Gemini 4 Neon.
- Pass Frontier models 8 of the top 10 have a score, led by GPT-6.2 Astra (#1).
- Pass Headroom The best is 75%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on cwe-bench.com: 20 rows for models we track at the last read.
- Pass Last read November 19th, 2026.
- Pass Read worked The last read worked.
Consistency 2 pass
- Pass Lab claims The one pair agrees within 10 points.
- Pass Known issues No published audit found problems.