CritPt ↗12%
MiMo-V2.6 Flash · CritPt · Accuracy · % ↗
Xiaomi / MODEL EVIDENCE
MiMo V2.6 Flash
30 benchmarks · 33 observations · 32 sources · released 2026-09-21
Scores at a glance
30 benchmarks · large dot: MiMo V2.6 Flash; small dots: closest models where reported
ProofBench ↗63 %
MiMo V2.6 Flash · ProofBench · Accuracy ↗
1 more reported result
63% · MiMo-V2.6 Flash · ProofBench · Accuracy · % · Epoch AI · ProofBench ↗
SciCode ↗51.27%
MiMo-V2.6 Flash · SciCode · Score · % ↗
Vals Index ↗54.83 %
MiMo V2.6 Flash · Vals Index · Accuracy ↗
Vals Finance Index ↗57.15 %
MiMo V2.6 Flash · Vals Finance Index · Accuracy ↗
Vals Legal Index ↗68.99 %
MiMo V2.6 Flash · Vals Legal Index · Accuracy ↗
Vals Science Index ↗31.72 %
MiMo V2.6 Flash · Vals Science Index · Accuracy ↗
Legal Research Bench ↗37.98 %
MiMo V2.6 Flash · Legal Research Bench · All-Pass ↗
HLAB-Vals-1.1 ↗13.33 %
MiMo V2.6 Flash · HLAB-Vals-1.1 · Task Pass Rate ↗
MiMo V2.6 Flash · Harvey's Legal Agent Benchmark v1 · Accuracy ↗
Vals Finance Agent v2.1 ↗63.32 %
MiMo V2.6 Flash · Finance Agent · Accuracy ↗
MiMo V2.6 Flash · Excel Modeling Benchmark · Accuracy ↗
1 more reported result
65.46 % · MiMo V2.6 Flash · Excel Modeling Benchmark v1 · Accuracy · Vals AI · Excel Modeling Benchmark v1 ↗
Tax Agent Bench ↗28.51 %
MiMo V2.6 Flash · Tax Agent Bench · Accuracy ↗
Vals Finance Agent v2 ↗56.28 %
MiMo V2.6 Flash · Finance Agent v2 · Accuracy ↗
MedCode ↗41.06 %
MiMo V2.6 Flash · MedCode · Accuracy ↗
MedScribe ↗85.28 %
MiMo V2.6 Flash · MedScribe · Accuracy ↗
MiMo V2.6 Flash (Mini-SWE-agent) · Terminal-Bench-Science · Score ↗
BioMysteryBench ↗69.26 %
MiMo V2.6 Flash · BioMysteryBench · Accuracy ↗
MysteryMechanism ↗21.62 %
MiMo V2.6 Flash · MysteryMechanism · Accuracy ↗
MiMo V2.6 Flash · SAGE · Accuracy ↗
Vibe Code Bench ↗78.96 %
MiMo V2.6 Flash (OpenHands) · Vibe Code Bench · original task set ↗
Code Migration v1.1 ↗39.55 %
MiMo V2.6 Flash · Code Migration · Accuracy ↗
1 more reported result
40.93 % · MiMo V2.6 Flash · Code Migration v1 · Accuracy · Vals AI · Code Migration v1 ↗
ProgramBench ↗0.5 %
MiMo V2.6 Flash · ProgramBench · Accuracy ↗
Terminal-Bench 4.0 ↗24.24 %
MiMo V2.6 Flash (Mini-SWE-agent) · Terminal-Bench 4.0 · Score ↗
IOI v1 & IOI v2 ↗47.67 %
MiMo V2.6 Flash · IOI · Accuracy ↗
CyberBench v1.1 ↗75.36 %
MiMo V2.6 Flash · CyberBench · Accuracy ↗
SRE-Bench ↗4.2 %
MiMo V2.6 Flash · SRE Bench · Accuracy ↗
Public Benefits Bench v1.1 ↗67.59 %
MiMo V2.6 Flash · Public Benefits Bench · Accuracy ↗
MiMo-v2.6-Flash (high) · Humanity's Sixth Sense · Score ↗
ALE-Bench ↗1244.2 Performance points
mimo-v2.6-flash · Average contest performance ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
DeepSeek V4.1 Flash →DeepSeek
20 of 27 shared benchmark comparisons
MiMo V2.6 Pro →Xiaomi
21 of 27 shared benchmark comparisons
20 of 27 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- SciCode Benchmark | Artificial Analysis ↗
- Ale Bench — methodology and published results ↗
- CritPt v1 ↗
- Humanity's Sixth Sense — evaluation methodology and results ↗
- BioMysteryBench — evaluation methodology and results ↗
- Code Migration v1 — evaluation methodology and results ↗
- Code Migration — evaluation methodology and results ↗
- CyberBench — evaluation methodology and results ↗
- Excel Modeling Benchmark v1 — evaluation methodology and results ↗
- Excel Modeling Benchmark — evaluation methodology and results ↗
- Finance Agent v2 — evaluation methodology and results ↗
- Finance Agent — evaluation methodology and results ↗
- Vals Finance Index — evaluation methodology and results ↗
- HLAB-Vals-1.1 — evaluation methodology and results ↗
- Harvey's Legal Agent Benchmark v1 — evaluation methodology and results ↗
- IOI — evaluation methodology and results ↗
- Vals Legal Index — evaluation methodology and results ↗
- Legal Research Bench — evaluation methodology and results ↗
- MedCode — evaluation methodology and results ↗
- MedScribe — evaluation methodology and results ↗
- MysteryMechanism — evaluation methodology and results ↗
- ProgramBench — evaluation methodology and results ↗
- ProofBench — evaluation methodology and results ↗
- Public Benefits Bench — evaluation methodology and results ↗
- SAGE — evaluation methodology and results ↗
- Vals Science Index — evaluation methodology and results ↗
- SRE Bench — evaluation methodology and results ↗
- Tax Agent Bench — evaluation methodology and results ↗
- Terminal-Bench 4.0 — evaluation methodology and results ↗
- Terminal-Bench-Science — evaluation methodology and results ↗
- Vals Index — evaluation methodology and results ↗
- Vibe Code Bench — evaluation methodology and results ↗
Names used in source tables
MiMo V2.6 Flash · MiMo V2.6 Flash (Mini-SWE-agent) · MiMo V2.6 Flash (OpenHands) · MiMo-V2.6 Flash · MiMo-v2.6-Flash (high) · mimo-v2.6-flash