chini-003-twitter-timeline
Social Timeline (Twitter-style fanout)
Generate a personalized timeline for millions of users. Don't melt when a celebrity posts.
Source: Classic system-design interview corpus (Twitter / Instagram timeline)
Prompt
Design the timeline-generation system for a social network. Functional: - POST /tweet appends a post by a user. - GET /timeline returns the most recent posts from accounts a user follows. - Reads vastly outnumber writes (~100:1). Non-functional: - A celebrity post (high-fanout write) must NOT degrade timeline reads for other users. - Survive a 10x read spike (a viral event). - A timeline-cache failure should degrade gracefully (slower reads), not drop posts. Return a Chinilla CanvasState. You will likely need a write path, a read path, a cache, and some kind of fanout/queue between them. Include a rate-limit behavior on the write side.
Constraints
- Max components
- 14
- Required behaviors
- queue, ratelimit, storage
- Monthly budget
- $1500
Stress scenarios
Baseline reads + writes
baselineMixed traffic at normal rates.
10x viral spike
spikeRead traffic explodes 10x. Reads must survive even if write path slows.
Timeline cache failure
outageCache layer drops out. Reads must fall back, not error.
Noisy network
cascadeProcess-time jitter at 25%. Tests resilience to flaky internal calls.
Pass criteria (overall)
- Min stability score
- 70
- Max drop rate
- 5.0%
- Min delivery rate
- 90.0%
- Max errors
- 5
Submit your run
Submissions go through the chini-bench CLI. It calls your model with your key, scores the result locally, and posts to the leaderboard. Nothing leaves your machine except the canvas it produces.
End-to-end:
pip install git+https://github.com/collapseindex/chini-bench-cli.git
export OPENROUTER_API_KEY=...
chini-bench run chini-003-twitter-timeline \
--provider openrouter --model google/gemini-2.0-flash-001 \
--as aliceOr inspect the prompt first:
chini-bench prompt chini-003-twitter-timeline Providers: openai · anthropic · google · openrouter · ollama
Leaderboard
| Rank | Submitter | Model | Score | Stability | Delivery | Design | Pass |
|---|---|---|---|---|---|---|---|
| #1 | rl_v06_run2 | rl_policy custom single-shot | 89 | 77.0 | 100.0 | 75.0 | ✗ |
| #2 | rl_v06_run2 | rl_policy custom single-shot | 87 | 74.0 | 100.0 | 75.0 | ✗ |
| #3 | rl_v06_run1 | rl_policy custom single-shot | 86 | 72.0 | 100.0 | 75.0 | ✗ |
| #4 | rl_v06_run2 | rl_policy custom single-shot | 86 | 81.0 | 84.0 | 75.0 | ✗ |
| #5 | rl_v06_run2 | rl_policy custom single-shot | 86 | 81.0 | 100.0 | 25.0 | ✗ |
| #6 | rl_v06_run2 | rl_policy custom single-shot | 85 | 69.0 | 100.0 | 75.0 | ✗ |
| #7 | rl_v06_run2 | rl_policy custom single-shot | 85 | 75.0 | 100.0 | 50.0 | ✗ |
| #8 | rl_v06_run2 | rl_policy custom single-shot | 85 | 83.0 | 85.0 | 75.0 | ✗ |
| #9 | rl_v06_run2 | rl_policy custom single-shot | 85 | 80.0 | 100.0 | 25.0 | ✗ |
| #10 | rl_v06_run2 | rl_policy custom single-shot | 85 | 80.0 | 83.0 | 75.0 | ✗ |
| #11 | rl_v06_run2 | rl_policy custom single-shot | 84 | 79.0 | 81.0 | 75.0 | ✗ |
| #12 | rl_v06_run2 | rl_policy custom single-shot | 84 | 80.0 | 88.0 | 75.0 | ✗ |
| #13 | rl_v06_run1 | rl_policy custom single-shot | 82 | 80.0 | 90.0 | 25.0 | ✗ |
| #14 | rl_v06_run2 | rl_policy custom single-shot | 82 | 74.0 | 92.0 | 50.0 | ✗ |
| #15 | rl_v06_run1 | rl_policy custom single-shot | 81 | 80.0 | 88.0 | 25.0 | ✗ |
| #16 | rl_v06_run2 | rl_policy custom single-shot | 81 | 66.0 | 100.0 | 50.0 | ✗ |
| #17 | rl_v06_run2 | rl_policy custom single-shot | 81 | 66.0 | 100.0 | 50.0 | ✗ |
| #18 | rl_v06_run2 | rl_policy custom single-shot | 81 | 81.0 | 84.0 | 25.0 | ✗ |
| #19 | rl_v06_run2 | rl_policy custom single-shot | 81 | 71.0 | 100.0 | 25.0 | ✗ |
| #20 | rl_v06_run2 | rl_policy custom single-shot | 81 | 77.0 | 75.0 | 75.0 | ✗ |
| #21 | rl_v06_run2 | rl_policy custom single-shot | 81 | 80.0 | 70.0 | 75.0 | ✗ |
| #22 | alex | x-ai/grok-4.20 default reflexion | 80 | 79.0 | 68.0 | 100.0 | ✗ |
| #23 | rl_v06_run2 | rl_policy custom single-shot | 80 | 78.0 | 69.0 | 75.0 | ✗ |
| #24 | rl_v06_run2 | rl_policy custom single-shot | 80 | 79.0 | 68.0 | 75.0 | ✗ |
| #25 | rl_v06_run2 | rl_policy custom single-shot | 80 | 80.0 | 84.0 | 25.0 | ✗ |
| #26 | rl_v06_run2 | rl_policy custom single-shot | 80 | 79.0 | 68.0 | 75.0 | ✗ |
| #27 | rl_v06_run2 | rl_policy custom single-shot | 80 | 79.0 | 68.0 | 75.0 | ✗ |
| #28 | alex | google/gemini-3.1-pro-preview default single-shot | 79 | 57.0 | 100.0 | 100.0 | ✗ |
| #29 | rl_v06_run1 | rl_policy custom single-shot | 79 | 79.0 | 83.0 | 35.0 | ✗ |
| #30 | rl_v06_run1 | rl_policy custom single-shot | 79 | 78.0 | 68.0 | 75.0 | ✗ |
| #31 | rl_v06_run1 | rl_policy custom single-shot | 79 | 78.0 | 68.0 | 75.0 | ✗ |
| #32 | rl_v06_run2 | rl_policy custom single-shot | 79 | 78.0 | 68.0 | 75.0 | ✗ |
| #33 | rl_v06_run2 | rl_policy custom single-shot | 79 | 67.0 | 100.0 | 25.0 | ✗ |
| #34 | rl_v06_run2 | rl_policy custom single-shot | 79 | 78.0 | 68.0 | 75.0 | ✗ |
| #35 | rl_v06_run2 | rl_policy custom single-shot | 79 | 77.0 | 75.0 | 75.0 | ✗ |
| #36 | alex | openai/gpt-5.4 default single-shot | 78 | 60.0 | 100.0 | 100.0 | ✗ |
| #37 | rl_v06_run1 | rl_policy custom single-shot | 78 | 76.0 | 65.0 | 75.0 | ✗ |
| #38 | rl_v06_run2 | rl_policy custom single-shot | 78 | 76.0 | 65.0 | 75.0 | ✗ |
| #39 | rl_v06_run2 | rl_policy custom single-shot | 78 | 76.0 | 65.0 | 75.0 | ✗ |
| #40 | rl_v06_run2 | rl_policy custom single-shot | 78 | 77.0 | 65.0 | 75.0 | ✗ |
| #41 | rl_v06_run1 | rl_policy custom single-shot | 77 | 78.0 | 68.0 | 50.0 | ✗ |
| #42 | rl_v06_run1 | rl_policy custom single-shot | 77 | 79.0 | 82.0 | 25.0 | ✗ |
| #43 | rl_v06_run1 | rl_policy custom single-shot | 77 | 64.0 | 100.0 | 25.0 | ✗ |
| #44 | rl_v06_run2 | rl_policy custom single-shot | 77 | 78.0 | 68.0 | 50.0 | ✗ |
| #45 | rl_v06_run2 | rl_policy custom single-shot | 77 | 81.0 | 64.0 | 50.0 | ✗ |
| #46 | alex | anthropic/claude-sonnet-4.6 default single-shot | 76 | 52.0 | 100.0 | 100.0 | ✗ |
| #47 | alex | google/gemini-3.1-pro-preview default reflexion | 76 | 51.0 | 100.0 | 100.0 | ✗ |
| #48 | rl_v06_run1 | rl_policy custom single-shot | 76 | 77.0 | 65.0 | 50.0 | ✗ |
| #49 | rl_v06_run2 | rl_policy custom single-shot | 74 | 75.0 | 64.0 | 75.0 | ✗ |
| #50 | rl_v06_run2 | rl_policy custom single-shot | 74 | 78.0 | 68.0 | 25.0 | ✗ |
| #51 | rl_v06_run1 | rl_policy custom single-shot | 73 | 62.0 | 83.0 | 50.0 | ✗ |
| #52 | rl_v06_run1 | rl_policy custom single-shot | 73 | 77.0 | 66.0 | 25.0 | ✗ |
| #53 | rl_v06_run1 | rl_policy custom single-shot | 73 | 77.0 | 66.0 | 25.0 | ✗ |
| #54 | rl_v06_run2 | rl_policy custom single-shot | 73 | 76.0 | 65.0 | 25.0 | ✗ |
| #55 | rl_v06_run2 | rl_policy custom single-shot | 73 | 77.0 | 65.0 | 25.0 | ✗ |
| #56 | rl_v06_run2 | rl_policy custom single-shot | 73 | 77.0 | 66.0 | 25.0 | ✗ |
| #57 | alex | anthropic/claude-sonnet-4.6 default reflexion | 68 | 44.0 | 100.0 | 100.0 | ✗ |
| #58 | rl_v06_run2 | rl_policy custom single-shot | 68 | 80.0 | 34.0 | 75.0 | ✗ |
| #59 | rl_v06_run1 | rl_policy custom single-shot | 67 | 62.0 | 54.0 | 75.0 | ✗ |
| #60 | rl_v06_run1 | rl_policy custom single-shot | 64 | 62.0 | 53.0 | 50.0 | ✗ |
| #61 | alex | x-ai/grok-4.20 default single-shot | 42 | 16.0 | 47.0 | 100.0 | ✗ |
| #62 | alex | openai/gpt-5.4 default reflexion | 24 | 9.0 | 0.0 | 75.0 | ✗ |
Per-scenario breakdown of the top run
| Scenario | Health | Drop rate | Delivered | Pass |
|---|---|---|---|---|
| baseline | 81.0 | 0.0% | 280 | ✓ |
| viral-spike | 82.0 | 0.0% | 2520 | ✓ |
| cache-failure | 72.0 | 0.0% | 45 | ✓ |
| fanout-jitter | 73.0 | 5.3% | 71 | ✗ |