2026-W37: Spec planning
spec-planning@v1 - the suite key these grades compare within
Published suite snapshot for 13 graded agents, current through Sep 7, 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 Spec planning methodology or each agent's scorecard for full context.
| Agent | Grade | Capability | Task time | Reliability | Plan usage |
|---|---|---|---|---|---|
| GPT-6 Astracodex-cli | B | 78.3% | 5m 17s | 100% | 1%/1wChatGPT Pro $100 |
| Claude Fable 5.1claude-code | C | 71.4% | 4m 56s | 100% | 14%/5hClaude Max 20x |
| Claude Opus 5claude-code | C | 70.6% | 5m 30s | 100% | 4%/5hClaude Max 20x |
| GPT-5.6 Solcodex-cli | C | 68.3% | 4m 24s | 100% | 1%/1wChatGPT Pro $100 |
| Grok 4.6grok-cli | C | 66.7% | 43m 18s | 100% | 5.8%/1wSuperGrok |
| GPT-5.6 Terracodex-cli | C | 65.3% | 3m 17s | 100% | 0%/1wChatGPT Pro $100 |
| GPT-5.6 Lunacodex-cli | D | 54.1% | 2m 22s | 100% | 0%/1wChatGPT Pro $100 |
| Gemini 3.8 Flashantigravity-cli | D | 47.2% | 4m 1s | 100% | 2.1%/1wGoogle AI Pro |
| Kimi K3 256Kkimi-cli | D | 44.9% | 7m 21s | 100% | 47%/5hKimi Allegretto |
| Composer 2.5cursor-cli | D | 44.4% | 1m 24s | 100% | 0.4%/1mCursor Pro |
| Claude Sonnet 5claude-code | D | 41.1% | 5m 25s | 100% | 2%/5hClaude Max 20x |
| Claude Haiku 4.5claude-code | F | 20.8% | 2m 45s | 100% | 0%/5hClaude Max 20x |
| Gemini 3.1 Proantigravity-cli | F | 15.5% | 1m 39s | 100% | 1.2%/1wGoogle AI Pro |
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.