Benchmark: FawnBench by @fawnunwrap · topicAI Coding
FawnBench running deer, four budget models — MiniMax M3.1 Flash vs Claude Haiku 5.5 vs DeepSeek V4.1 Flash 1017 vs GPT-6.1 Terra
Scoreboard4
- MiniMax M3.1 FlashMiniMax
- Time
- 7.6 min
- Cost
- $0.016
- Tokens
- 28K
- Claude Haiku 5.5Anthropic
- Time
- 10.3 min
- Cost
- $0.081
- Tokens
- 205K
- DeepSeek V4.1 Flash 1017DeepSeek
- Time
- 4.7 min
- Cost
- $0.068
- Tokens
- 124K
- GPT-6.1 TerraOpenAI
- Time
- 35 s
- Cost
- $0.032
- Tokens
- 21K
FawnBench running deer, four budget modelsThe post doesn’t quote the prompt wording.
FawnBench round 2, the running deer: MiniMax M3.1 Flash, Claude Haiku 5.5, DeepSeek V4.1 Flash 1017 and GPT-6.1 Terra, picked by the poster as roughly the same price on Artificial Analysis.
The post, itemised
- Kind
- Side-by-side
- Task
- FawnBench running deer, four budget models
- Topic
- FawnBench (3D deer)
- Category
- 3D & Shaders
- Mode
- Not stated
- Posted
- Video length
- 16 s
- Likes
- 13
- Views
- 786
- Bookmarks
- 1
- Sponsored
- No
NotesModel names and figures from the labels in the video grid (Round 2, Running Deer).
Cost & time, as stated in the postAs shown on the video’s labels: MiniMax M3.1 7 min 35 s, 28K tokens, $0.016; Claude Haiku 5.5 10 min 21 s, 205K tokens, $0.081; DeepSeek V4.1 Flash 1017 4 min 40 s, 124K tokens, $0.068; GPT-6.1 Terra 35 s, 21K tokens, $0.032 (API cost).
Related
Posted by @fawnunwrap on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal
