Codesota · Models · MiMo-V2.5-Pro5 results · 5 benchmarks
Model card
MiMo-V2.5-Pro.
unknown
§ 02 · Benchmarks
Every benchmark MiMo-V2.5-Pro has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | GSM8K | Reasoning · Mathematical Reasoning | accuracy | 99.6% | #2 | — | source ↗ |
| 02 | HLE | Reasoning · Multi-step Reasoning | accuracy | 48.0% | #2 | — | source ↗ |
| 03 | SWE-Bench Verified | Computer Code · Code Generation | accuracy | 78.9% | #5 | — | source ↗ |
| 04 | GPQA Diamond | Reasoning · Multi-step Reasoning | accuracy | 66.7% | #53 | — | source ↗ |
| 05 | MMLU-Pro | Reasoning · Commonsense Reasoning | accuracy | 68.5% | #63 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where MiMo-V2.5-Pro actually performs.
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
5
results
0 of 5 rows marked verified.