MiMo-V2.6 Flash
MiMo-V2.6 Flash places in the top three on StructEval.
Xiaomi Corp Released 21 Sep 2026
35
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Xiaomi Corp Sep 2026
MiMo-V2.6 Flash
No Epoch Capabilities Index score yet
- Harvey LAB (Legal Agent Benchmark) 11.3% #16 /80
- CritPt 12% #54 /160
- Vals Finance Agent v2 56.3% #21 /80
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMArena (Elo) | 1,448 | #66 of 333 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ProofBench | 63% | #21 of 83 | Epoch AI | |
| CritPt | 12% | #54 of 160 | Epoch AI | |
| ProofBench v1.1 | 63% | #21 of 51 | Official leaderboard | |
| MysteryMechanism | 21.6% | #22 of 29 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| StructEval | 79.6% | #3 of 28 | Official leaderboard | |
| Code Arena | 1,637 | #20 of 124 | Official leaderboard | |
| Vibe Code Bench | 79% | #30 of 115 | Official leaderboard | |
| Image-to-WebDev Arena | 1,596 | #17 of 55 | Official leaderboard | |
| ALE-Bench | 1,244 | #38 of 121 | Epoch AI | |
| Code Migration | 40.9% | #30 of 78 | Official leaderboard | |
| IOI v2 (Vals) | 47.7% | #28 of 45 | Official leaderboard | |
| Code Migration v1.1 | 39.5% | #20 of 29 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Agent Arena | 0.01 | #27 of 53 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Harvey LAB (Legal Agent Benchmark) | 11.3% | #16 of 80 | Official leaderboard | |
| Vals Finance Agent v2 | 56.3% | #21 of 80 | Official leaderboard | |
| Public Benefits Bench | 67.6% | #14 of 50 | Official leaderboard | |
| MedScribe | 85.3% | #29 of 98 | Official leaderboard | |
| Excel Modeling Benchmark | 65.5% | #24 of 76 | Official leaderboard | |
| Vals Finance Agent v2.1 | 63.3% | #12 of 35 | Official leaderboard | |
| Harvey LAB v1.1 (HLAB-Vals-1.1) | 13.3% | #13 of 33 | Official leaderboard | |
| Tax Agent Bench | 28.5% | #33 of 79 | Official leaderboard | |
| Vals Finance Index | 57.1% | #16 of 35 | Official leaderboard | |
| Legal Research Bench | 38% | #41 of 88 | Official leaderboard | |
| Vals Legal Index | 69% | #18 of 33 | Official leaderboard | |
| MedCode | 41.1% | #55 of 96 | Official leaderboard | |
| Vals Index v2.2 | 54.8% | #19 of 32 | Official leaderboard | |
| Excel Modeling Benchmark v1.1 | 68.9% | #22 of 37 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vision Arena | 1,245 | #51 of 136 | Official leaderboard | |
| Humanity's Sixth Sense | 25.4% | #22 of 29 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CyberBench v1.1 (Vals) | 75.4% | #7 of 43 | Official leaderboard | |
| SRE-Bench | 4.20% | #16 of 33 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SAGE (Vals) | 43.5% | #48 of 81 | Official leaderboard | |
| Vals Science Index | 31.7% | #17 of 23 | Official leaderboard | |
| SAGE v1.1 (Vals) | 83.3% | #21 of 28 | Official leaderboard |