MirrorCode leaderboard
- Claude Opus 5.5 leads
- 77.4%
- models measured
- 9
- lead over #2
- +4.1 pts
- median
- 31.1%
Leader on MirrorCode · read October 21
# MirrorCode, read October 21
leaders = {
"Claude Opus 5.5": 77.4%, "Claude Fable 5.1": 73.3%, "Claude Fable 5": 63.9%,
}
On October 21, 2026, 9 of our catalog's models had a MirrorCode result, and Anthropic Claude Opus 5.5 led with 77.4%.
Epoch AI collects its results; its benchmarking hub describes the tasks and links the authors.
Role in the index
A coding board we show beside the Vibe Coding Index, not inside it: the index keeps the four boards it was defined on, so a score does not move every time a board is added. Read the methodology
| # | Model | Result | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5Anthropic | 77.4% | 92.2 | $20.00 | |
| 2 | Claude Fable 5.1Anthropic | 73.3% | 89.1 | $50.00 | |
| 3 | Claude Fable 5Anthropic | 63.9% | 82.1 | $50.00 | |
| 4 | GPT-6 AstraOpenAI | 46.7% | 88.7 | $50.00 | |
| 5 | Claude Opus 4.7Anthropic | 31.1% | 51.1 | $25.00 | |
| 6 | GPT-5.6 SolOpenAI | 20.0% | 76.7 | $20.00 | |
| 7 | GPT-5.4OpenAI | 15.6% | 37.7 | $15.00 | |
| 8 | GPT-5.5OpenAI | 10.0% | 67.8 | $30.00 | |
| 9 | Gemini 3.1 Pro PreviewGoogle | 8.9% | 35.3 | $12.00 |
Only models in our catalog are listed, and each appears once with its best published run. 197 rows were read from the source on October 21, 2026, and rows that match no catalog model are left out.