Vibe Code Bench
Vibe Code Bench results reported for 67 models across 6 versions. Updated 2026-10-07.
Report an issueVersions
6 versions · Metric: Vibe Code Bench Score
| Version | Released | Models | Results |
|---|---|---|---|
| Vibe Code Bench 1.1 — Claude Code, October 2026 evaluationConfiguration: Claude Code harness | October 6, 2026 | 2 | 2 |
| Vibe Code Bench 1.1 — Codex, October 2026 evaluationConfiguration: Codex harness | October 6, 2026 | 2 | 2 |
| Vibe Code Bench 1.1 — Cursor CLI, October 2026 evaluationConfiguration: Cursor CLI harness | October 6, 2026 | 1 | 1 |
| Vibe Code Bench 1.1 — Factory, October 2026 evaluationConfiguration: Factory harness | October 6, 2026 | 1 | 1 |
| Vibe Code Bench 1.1 — OpenHands, October 2026 evaluationConfiguration: OpenHands harness | October 6, 2026 | 65 | 66 |
| Vibe Code Bench 1.1 — OpenHands, September 2026 evaluationConfiguration: OpenHands harness | September 30, 2026 | 1 | 1 |
Recently reported results: Vibe Code Bench 1.1 — Claude Code, October 2026 evaluation, Claude Code harness
Most recent configuration: Vibe Code Bench 1.1 — Claude Code, October 2026 evaluation
| Model | Score | Source |
|---|---|---|
| Claude Opus 4.8 | 77.5% | vals.ai for Claude Opus 4.8 on Vibe Code Bench 1.1 — Claude Code, October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)Vibe Code Bench ScoreReported Benchmark leaderboardVals AIIndependentRecord for Claude Opus 4.8 on Vibe Code Bench 1.1 — Claude Code, October 2026 evaluation |
| Claude Sonnet 4.6 | 55.8% | vals.ai for Claude Sonnet 4.6 on Vibe Code Bench 1.1 — Claude Code, October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)Vibe Code Bench ScoreReported Benchmark leaderboardVals AIIndependentRecord for Claude Sonnet 4.6 on Vibe Code Bench 1.1 — Claude Code, October 2026 evaluation |