MiMo Code Bench

Claude Opus 5 68.6% leads since September 2026

In use

Coding agents work through a varied set of software tasks built in house by Xiaomi. The report gives no task count or grading details.

Xiaomi also reports a mini version with avg@3 during training.

Made by: Xiaomi MiMo
Released: September 2026
Kind: Fixing real repositories
Level: Expert
Scored: Checked automatically
Answers: Agent task
Tasks: Kept private

Strongest model tested: GPT-6 Astra #3 on the capability index
Last in a launch post: September 2026
Last model added: September 2026
Scores refreshed: November 12th, 2026

Paper huggingface.co

Models scored on its own leaderboard

Launch post lists it, from 1 lab

System card reports it, from 1 lab

Claude Opus 5 leads with 68.6% among models released by September 2026

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

Bars Table

The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

1 Claude Opus 5 68.6%
2 MiMo-V2.6 Pro 63.2%
3 GPT-6 Astra 61.4%
4 MiMo-V2.6 Flash 61.2%
5 DeepSeek V4.1 Flash 60.2%
6 Kimi K3 60.1%
7 GPT-5.6 Sol 59.3%
8 MiMo-V2.5-Pro 40.4%

Source: Official MiMo Code Bench leaderboard

#	Model	Score	Date	Source
1	Claude Opus 5	68.6%	Jul 2026	Official leaderboard
2	MiMo-V2.6 Pro	63.2%	Sep 2026	Official leaderboard
3	GPT-6 Astra	61.4%	Sep 2026	Official leaderboard
4	MiMo-V2.6 Flash	61.2%	Sep 2026	Official leaderboard
5	DeepSeek V4.1 Flash	60.2%	Sep 2026	Official leaderboard
6	Kimi K3	60.1%	Jul 2026	Official leaderboard
7	GPT-5.6 Sol	59.3%	Jul 2026	Official leaderboard
8	MiMo-V2.5-Pro	40.4%	Apr 2026	Official leaderboard

Labs report scores for 1 model in their cards. We plot every source in the charts below.

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic

Own leaderboard Not tested since Sep 2026

Claude Opus 5 68.6%

Source: Official MiMo Code Bench leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far

Sources: Official MiMo Code Bench leaderboard and labs’ model cards

One lab put it in a launch post in the last six months

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.

Xiaomi Corp

Date	Launch post	Score	As the post writes it
Sep 22, 2026	MiMo-V2.6 Pro	63.2	MiMo Code Bench

One system card reports it

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

Date	Document	Score	As the document writes it	Section
Sep 22, 2026	MiMo-V2.6 Pro technical report	63.2	MiMo Code Bench (in-house) (Table 3)	Capabilities

One lab claim next to the leaderboard

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.

Model	Lab says	Board says	Gap
MiMo-V2.6 Pro	63.2% MiMo Code Bench	63.2% Leaderboard	Same