MAI Code 2 Coding Benchmark
How MAI Code 2 ranks on the LLM Coding Leaderboard, shown next to the three models directly above and below it, with the top three models included for reference.
Last evaluated: 1 day ago (November 20, 2026), with OpenCode.
| # | Model | Total points (max 90) |
Avg cost per prompt |
Avg time per prompt |
Video | Tested with | Points per project | Consistency penalty | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
Laravel Code Quality
(max 20) |
React-TS Code Quality
(max 20) |
Bug Finding Test
(max 10) |
Python Code Quality
(max 20) |
Edge-case Testing (4 projects, max 20) |
||||||||
| 1 | Opus 5.5 (High) | 84.95 | $0.83 | 03:42 |
Claude Code |
18.68 | 19 | 9.1 | 18.17 | 20 | 0 | |
| 2 | Fable 5.2 (Medium) | 84.7 | $1.42 | 03:03 |
Claude Code |
19.13 | 19.5 | 9.52 | 17.8 | 18.75 | 0 | |
| 3 | GPT-6-Astra (High) | 84.25 | $0.96 | 04:34 |
Codex CLI |
18.6 | 18.17 | 9.03 | 18.47 | 20 | −0.02 | |
| ⋯ 14 places not shown ⋯ | ||||||||||||
| 18 | Opus 5.5 (Low) | 78.19 | $0.37 | 01:21 |
Claude Code |
17.37 | 18.17 | 6.63 | 18.1 | 18.5 | −0.58 | |
| 19 | Gemini 4 Hydrogen (High) | 78.01 | N/A | 03:42 |
Antigravity |
18.23 | 17.33 | 7.92 | 16.27 | 18.75 | −0.49 | |
| 20 | GPT-6.1-Terra (Max) | 77.67 | $0.27 | 07:55 |
Codex CLI |
17.82 | 18.17 | 8.61 | 16.7 | 16.5 | −0.13 | |
| 21 | MAI Code 2 (High) | 77.66 | $0.20 | 05:41 |
OpenCode |
17.63 | 17.17 | 6.96 | 17.4 | 19.25 | −0.75 | |
| 22 | Gemini 4 Neon (Medium) | 77.34 | N/A | 03:57 |
Antigravity |
16.95 | 18 | 8.02 | 16.87 | 17.5 | 0 | |
| 23 | Deepseek-V4.1-Flash-1017 (Max) | 77.08 | $0.07 | 07:09 |
OpenCode |
17.42 | 18.17 | 8.47 | 16.27 | 17.25 | −0.50 | |
| 24 | Haiku 5.5 (High) | 76.3 | $0.05 | 03:37 |
Claude Code |
17.3 | 18 | 7.22 | 17.23 | 17.25 | −0.70 | |
Videos about MAI Code 2
Video
· Nov 21, 2026
I Tested New MAI Code 2 LLMs from Microsoft on Coding
How to read this
- Each score measures a model-and-harness configuration, not the model in isolation.
- Prices are calculated with API costs. Models tested on a subscription plan show N/A.
- Full methodology and scoring formulas are explained in this article.
See every tested model side by side on the full LLM Coding Leaderboard.