Skip to main content

Benchmark profile

Vals CyberBench (CyberBench)

Can autonomous agents craft PoC inputs that trigger OSS-Fuzz vulnerabilities—and stop crashing after the fix?

Data verified

How BenchLM shows CyberBench

BenchLM mirrors the public Vals AI CyberBench leaderboard captured from https://www.vals.ai/benchmarks/cyber and updated by Vals on July 17, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

CyberBench is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.

17 Vals rows3 task viewsprivate datasetTasks: Overall, PoC, PatchDisplay only

CyberBench score on CyberBench — July 17, 2026

BenchLM mirrors the published cyberbench score view for CyberBench. GPT-5.6 Sol leads the public snapshot at 88.14% , followed by GPT-5.6 Luna (83.90%) and GPT-5.5 (80.51%). BenchLM does not use these results to rank models overall.

17 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated July 17, 2026

CyberBench score table (17 models)

Score
1
88.14%
2
83.90%
3
GPT-5.5OpenAI
80.51%
4
Kimi K3Moonshot AI
79.03%
5
77.36%
6
MiniMax M3MiniMax
76.27%
7
Kimi K2.6Moonshot AI
74.35%
8
GPT-5.4OpenAI
72.88%
9
69.33%
10
68.64%
11
66.72%
12
InklingThinkingmachines
64.14%
13
52.14%
14
50.85%
15
Grok 4.3SpaceXAI
47.46%
16
37.50%

The published CyberBench snapshot places GPT-5.6 Sol first at 88.14%. The third row is 7.63 points behind. The broader top-10 range is 19.49 points, so the table still separates the published systems.

17 models have been evaluated on CyberBench. The benchmark falls in the External benchmark mirrors category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. CyberBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About CyberBench

Year

2026

Tasks

OSS-Fuzz PoC and patch-verification tasks

Format

Accuracy score

Difficulty

Autonomous cybersecurity exploit reproduction

BenchLM mirrors the public Vals AI CyberBench leaderboard as display-only external evidence. The captured snapshot preserves overall scores, task-level scores where Vals publishes them, uncertainty, latency, and cost-per-test metadata. It is excluded from BenchLM weighted rankings.

BenchLM freshness & provenance

Version

CyberBench 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does CyberBench measure?

Can autonomous agents craft PoC inputs that trigger OSS-Fuzz vulnerabilities—and stop crashing after the fix?

Which model leads the published CyberBench snapshot?

GPT-5.6 Sol currently leads the published CyberBench snapshot with 88.14% cyberbench score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on CyberBench?

17 AI models are included in BenchLM's mirrored CyberBench snapshot, based on the public leaderboard captured on July 17, 2026.

Last updated: July 17, 2026 · mirrored from the public benchmark leaderboard

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.