Benchmark profile
VulcanBench v3
An open software-engineering benchmark built from real merged post-cutoff pull requests across Python, Rust, TypeScript, JavaScript, and Go repositories.
Data verifiedBenchmark score on VulcanBench v3 — July 21, 2026
BenchLM mirrors the published score view for VulcanBench v3. Grok 4.5 leads the public snapshot at 91.3% , followed by GPT-5.6 Sol (87.0%) and Claude Fable 5 (87.0%). BenchLM does not use these results to rank models overall.
Grok 4.5
xAI
grok-4-5
GPT-5.6 Sol
OpenAI
gpt-5-6-sol
Claude Fable 5
Anthropic
claude-fable-5
Benchmark score table (3 models)
ScoreThe published VulcanBench v3 snapshot places Grok 4.5 first at 91.3%. The third row is 4.3 points behind. The broader top-10 range is 4.3 points, so many of the published results sit in a relatively narrow band.
3 models have been evaluated on VulcanBench v3. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. VulcanBench v3 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About VulcanBench v3
Year
2026
Tasks
23 post-cutoff repository tasks in the v3 report
Format
Pass@1 with low, medium, and high effort
Difficulty
Professional multi-file software engineering
VulcanBench v3 evaluates repository-level patches with deterministic hidden tests inside network-isolated Docker sandboxes. The July 2026 three-way report contains 23 gold-validated tasks, one attempt per task at low, medium, and high effort, and full run traces. We store each model's best published configuration as a display-only benchmark-owned result.
BenchLM freshness & provenance
Version
VulcanBench v3 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
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 VulcanBench v3 measure?
An open software-engineering benchmark built from real merged post-cutoff pull requests across Python, Rust, TypeScript, JavaScript, and Go repositories.
Which model scores highest on VulcanBench v3?
Grok 4.5 by xAI currently leads with a score of 91.3% on VulcanBench v3.
How many models are evaluated on VulcanBench v3?
3 AI models have been evaluated on VulcanBench v3 on BenchLM.
Compare Top Models on VulcanBench v3
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.