2026-W39: Vibe coding
Week 39 of 2026 graded 13 coding agents on vibe coding. Claude Opus 5 leads with C+. The biggest move since W38 2026 is GPT-5.6 Luna, C- to F. Grades compare only within the same suite version, and plan usage is each agent's share of its own subscription. Every agent ran the same suite cut headless through its own tools.Measured
vibe-coding@v1 - the suite key these grades compare within
Published suite snapshot for 13 graded agents, current through Sep 22, 2026.
Sorted by capability. Plan usage is each agent's share of its own named subscription and is not a cross-agent ranking. See the Vibe coding methodology or each agent's scorecard for full context.
| Agent | Grade | Capability | Clears | Task time | Reliability | Plan usage |
|---|---|---|---|---|---|---|
| Claude Opus 5claude-code | C+ | 71.6% | level 2 · partial level 5 | 2m 51s | 100% | 1.6%/5hClaude Max 5x |
| GPT-6 Astracodex-cli | C- | 61.3% | level 2 · partial level 5 | 2m 46s | 100% | 0.2%/1wChatGPT Pro 5x |
| Grok 4.6grok-cli | C- | 61.3% | level 2 · partial level 5 | 11m 4s | 100% | 0%/1wSuperGrok Plus |
| Kimi K3 256Kkimi-cli | C- | 60.0% | none | 6m 33s | 100% | 14%/5hKimi Allegretto |
| Claude Fable 5.1claude-code | C- | 58.7% | level 3 · partial level 5 | 3m 58s | 100% | 6.2%/5hClaude Max 5x |
| Gemini 3.8 Flashantigravity-cli | D+ | 52.3% | level 1 · partial level 5 | 6m 42s | 100% | 1.2%/1wGoogle AI Pro |
| Claude Sonnet 5claude-code | D+ | 51.0% | level 1 · partial level 5 | 4m 26s | 100% | 2.4%/5hClaude Max 5x |
| GPT-5.6 Solcodex-cli | D+ | 51.0% | level 2 · partial level 5 | 3m 46s | 100% | 0.4%/1wChatGPT Pro 5x |
| Gemini 3.1 Proantigravity-cli | F | 34.8% | none | 4m 3s | 100% | 1.0%/1wGoogle AI Pro |
| GPT-5.6 Terracodex-cli | F | 34.2% | level 1 · partial level 5 | 5m 32s | 100% | 0%/1wChatGPT Pro 5x |
| Composer 2.5cursor-cli | F | 31.6% | none | 1m 56s | 100% | 0.2%/1mCursor Pro |
| GPT-5.6 Lunacodex-cli | F | 25.2% | level 1 · partial level 5 | 3m 40s | 100% | 0%/1wChatGPT Pro 5x |
| Claude Haiku 4.5claude-code | F | 22.6% | none | 3m 36s | 100% | 2%/5hClaude Max 5x |
This page publishes aggregate outcomes only. Task prompts and private checker logic never leave the benchmark. Follow this suite over time on Grades over time.