agents benchmark
MiMo Coding Bench
MiMo Coding Bench evaluates coding-agent capabilities on software engineering tasks reported with the MiMo model family.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
MiMo Coding Bench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | XI | 73.7% | 100.0% | 2 | C | |
| 2 | XI | 71.8% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
MiMo Coding Bench highlights
The top published results on this benchmark's own scale.
What is MiMo Coding Bench?
Definition and scoring fields from the benchmark registry.
MiMo Coding Bench evaluates coding-agent capabilities on software engineering tasks reported with the MiMo model family.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MiMo Coding Bench
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mimo-coding-bench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MiMo Coding Bench.
Which model scores highest on MiMo Coding Bench?
MiMo-V2.5-Pro is currently ranked first with 73.7%.
What does MiMo Coding Bench measure?
MiMo Coding Bench evaluates coding-agent capabilities on software engineering tasks reported with the MiMo model family.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.