MiMo Coding Bench
MiMo-V2.5-Pro 73.7% Fading
Models do varied coding tasks inside agent harnesses such as Claude Code. Tasks cover repo understanding, project building, code review, artifact generation, planning and SWE.
Xiaomi built it in house. The MiMo-V2.6 report uses a MiMo Code Bench that gives MiMo-V2.5-Pro 40.4 against 73.7 here, so the two sets differ.
Made by Xiaomi MiMo Released Apr 2026 Fixing real repositories Tasks kept private Last in a launch post Apr 2026 , dropped before it saturated
Last model added Apr 2026
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
2
Models scored in lab cards
2
Launch posts list it, from 1 lab
MiMo-V2.5-Pro leads with 73.7%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 MiMo-V2.5-Pro 73.7%
- 2 MiMo-V2.5 71.8%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | MiMo-V2.5-Pro | 73.7% | Apr 2026 | Model card | |
| 2 | MiMo-V2.5 | 71.8% | Apr 2026 | Model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Reported by the lab in its model card
Best so far
Labs headline it less often now, last in Apr 2026
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 27 Apr 2026 | MiMo-V2.5-Pro | 73.7 | MiMo Coding Bench |
| 22 Apr 2026 | MiMo-V2.5 | 71.8 | MiMo Coding Bench |
More in Coding
- SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
- SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Opus 5.5 93.9%
- LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests.
DeepSeek-V4-Pro 93.5% - DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
- SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases.
Seed2.1 Pro 59.8% - Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471