Harness comparisonAI Coding
Tetris in three agents: Claude Code, Codex, DeepSeek — Claude Code (Claude Opus 5.5) vs OpenAI Codex (GPT-6.1 Sol) vs DeepSeek Harness (DeepSeek V4 Pro 0813)
Scoreboard3
- Claude Opus 5.5AnthropicClaude Code
- Time
- 4 min
- Playable; its AI clears lines
- GPT-6.1 SolOpenAIOpenAI Codex
- Time
- 3.4 min
- Playable; cheapest of the three
- DeepSeek V4 Pro 0813DeepSeekDeepSeek Harness
- Time
- 3.4 min
- medium confidence
- Playable, but its turn ended mid self-test
- Written “V4 Pro” without a date; mapped to DeepSeek V4 Pro 0813.
Prompt
Topic · Tetris cloneTetris in three agents: Claude Code, Codex, DeepSeekThe post doesn’t quote the prompt wording.
Same Tetris prompt in three agents: Claude Code with Claude Opus 5.5 (3:58, $0.60), Codex with GPT-6.1 Sol (3:25, $0.16) and DeepSeek Harness with DeepSeek V4 Pro (3:24, $0.26). All three games are playable.
Each side pairs a coding harness with its own model, so harness and model differences are mixed. More Claude Code vs OpenAI Codex. More OpenAI Codex vs DeepSeek Harness. All harness comparisons.
The post, itemised
- Task
- Tetris in three agents: Claude Code, Codex, DeepSeek
- Topic
- Tetris clone
- Category
- Games
- Mode
- Not stated
- Posted
- Video length
- 24 s
- Likes
- 1
- Views
- 134
- Bookmarks
- 0
- Sponsored
- No
Cost & time, as stated in the postAs stated: Claude Code 3:58, $0.60; Codex 3:25, $0.16; DeepSeek Harness 3:24, $0.26.
Related
Content belongs to its creators. Video by @agentsky_dev; aivs.tv hosts a copy for fast playback and links to the original post on X. Request removal
