SWE-2 Flash Coding Benchmark
How SWE-2 Flash 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: 3 days ago (November 7, 2026), with Devin.
| # | 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) | 85.43 | $0.83 | 03:42 |
Claude Code |
18.68 | 19 | 9.58 | 18.17 | 20 | 0 | |
| 2 | GPT-6-Astra (High) | 84.82 | $0.96 | 04:34 |
Codex CLI |
18.6 | 18.17 | 9.58 | 18.47 | 20 | 0 | |
| 3 | GPT-6-Astra (Medium) | 84.53 | $0.69 | 03:08 |
Codex CLI |
18.2 | 17.83 | 10 | 18.5 | 20 | 0 | |
| ⋯ 24 places not shown ⋯ | ||||||||||||
| 28 | GLM-5.3 (High) | 69.99 | $0.19 | 04:58 |
OpenCode |
17.55 | 17.67 | 4.9 | 16.27 | 14.7 | −1.10 | |
| 29 | Qwen 3.8 Max (0902) (High) | 69.99 | $0.40 | 11:49 |
OpenCode |
17.75 | 18 | 4.69 | 17.7 | 12.95 | −1.10 | |
| 30 | GPT-6.1-Terra (High) | 69.59 | $0.05 | 00:46 |
Codex CLI |
16.12 | 16.17 | 8.13 | 14.77 | 14.4 | 0 | |
| 31 | SWE-2 Flash (High) | 68.55 | N/A | 11:29 |
Devin |
17.4 | 17.33 | 4.17 | 17.4 | 13 | −0.75 | |
| 32 | GPT-6.1-Terra (Medium) | 68.5 | $0.04 | 00:31 |
Codex CLI |
16.28 | 16.17 | 7.71 | 15.67 | 14.45 | −1.78 | |
| 33 | MiMo-V2.6 Pro (High) | 68.44 | $0.09 | 15:04 |
OpenCode |
17.41 | 18 | 6.25 | 15.23 | 12.15 | −0.60 | |
| 34 | GPT-6-Luna (High) | 67.47 | $0.01 | 03:51 |
Codex CLI |
16.9 | 15.83 | 5.31 | 15.53 | 15 | −1.10 | |
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.