2026-W37: Real-world issues
real-world@v3 - 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 Real-world issues methodology or each agent's scorecard for full context.
| Agent | Grade | Capability | Clears | Task time | Reliability | Plan usage |
|---|---|---|---|---|---|---|
| Gemini 3.8 Flashantigravity-cli | C | 73.3% | tier 4 · partial tier 5 | 5m 42s | 100% | 21.6%/1wGoogle AI Pro |
| Claude Fable 5.1claude-code | C | 73.3% | tier 4 · partial tier 5 | 2m 2s | 100% | 27%/5hClaude Max 20x |
| Composer 2.5cursor-cli | C | 60.0% | tier 4 · partial tier 5 | 1m 16s | 100% | 1.7%/1mCursor Pro |
| Grok 4.6grok-cli | C | 60.0% | tier 4 · partial tier 5 | 6m 14s | 100% | 3.0%/1wSuperGrok |
| Kimi K3 256Kkimi-cli | C | 60.0% | tier 4 · partial tier 5 | 3m 12s | 100% | 123%/5hKimi Allegretto |
| Claude Sonnet 5claude-code | C | 56.7% | tier 2 · partial tier 5 | 3m 14s | 100% | 5%/5hClaude Max 20x |
| GPT-5.6 Solcodex-cli | C | 56.7% | tier 2 · partial tier 5 | 2m 27s | 100% | 2%/1wChatGPT Pro $100 |
| GPT-5.6 Terracodex-cli | D | 53.3% | tier 3 · partial tier 5 | 2m 30s | 100% | 2%/1wChatGPT Pro $100 |
| GPT-5.6 Lunacodex-cli | D | 52.5% | none | 2m 12s | 100% | 0%/1wChatGPT Pro $100 |
| Claude Haiku 4.5claude-code | D | 51.7% | tier 1 · partial tier 5 | 3m 35s | 100% | 4%/5hClaude Max 20x |
| Claude Opus 5claude-code | D | 50.0% | tier 2 · partial tier 5 | 5m 8s | 100% | 10%/5hClaude Max 20x |
| Gemini 3.1 Proantigravity-cli | D | 46.7% | tier 3 · partial tier 5 | 3m 27s | 100% | 12.4%/1wGoogle AI Pro |
| GPT-6 Astracodex-cli | D | 43.3% | tier 2 · partial tier 5 | 2m 18s | 100% | 4%/1wChatGPT Pro $100 |
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.