Grok 4.6 vs MiMo V2.6 Flash: Benchmark Comparison

Grok 4.6 has the higher score on 10 of 16 shared benchmarks; MiMo V2.6 Flash leads on 6.

The largest observed score gap is 12.00 pts on ProofBench v1.1 , where MiMo V2.6 Flash leads.

Reported ±1 standard-error ranges overlap on 9 of 16 shared benchmarks with comparable uncertainty data. This is not a pairwise statistical significance test.

Shared benchmark results

Scores and reported standard errors come from the latest visible Vals benchmark version available for both models.

Benchmark Grok 4.6 MiMo V2.6 Flash Gap Reported uncertainty
Vals Science Index 38.09% ±1.64 31.72% ±1.27 6.37 pts Reported ±1 SE ranges do not overlap
Legal Research Bench 48.08% ±3.47 37.98% ±3.37 10.10 pts Reported ±1 SE ranges do not overlap
Tax Agent Bench 33.66% ±3.41 28.51% ±3.14 5.15 pts Reported ±1 SE ranges overlap
MedCode 44.71% ±2.26 41.06% ±2.03 3.66 pts Reported ±1 SE ranges overlap
MedScribe 86.53% ±1.96 85.28% ±1.99 1.26 pts Reported ±1 SE ranges overlap
ProofBench v1.1 51.00% ±5.02 63.00% ±4.85 12.00 pts Reported ±1 SE ranges do not overlap
BioMysteryBench 72.22% ±0.00 69.26% ±0.98 2.96 pts Reported ±1 SE ranges do not overlap
MysteryMechanism 30.63% ±3.10 21.62% ±2.77 9.01 pts Reported ±1 SE ranges do not overlap
Terminal-Bench-Science 11.43% ±3.83 4.29% ±2.44 7.14 pts Reported ±1 SE ranges do not overlap
IOI 47.61% ±2.09 47.67% ±4.79 0.06 pts Reported ±1 SE ranges overlap
ProgramBench 1.00% ±0.70 0.50% ±0.50 0.50 pts Reported ±1 SE ranges overlap
Terminal-Bench 4.0 17.17% ±1.34 24.24% ±1.51 7.07 pts Reported ±1 SE ranges do not overlap
Vibe Code Bench v1.1 76.24% ±3.82 78.96% ±4.04 2.72 pts Reported ±1 SE ranges overlap
CyberBench v1.1 67.68% ±5.87 75.36% ±5.42 7.68 pts Reported ±1 SE ranges overlap
Access to Justice Benchmark 71.34% ±0.73 70.75% ±0.73 0.60 pts Reported ±1 SE ranges overlap
Public Benefits Bench v1.1 66.85% ±1.23 67.59% ±1.22 0.74 pts Reported ±1 SE ranges overlap

Performance by category

Category Grok 4.6 average MiMo V2.6 Flash average
Legal 48.08% 37.98%
Finance 33.66% 28.51%
Healthcare 65.62% 63.17%
Math 51.00% 63.00%
Science 38.09% 31.72%
Coding 35.51% 37.84%
Cyber 67.68% 75.36%
Social Mobility 69.09% 69.17%

Cost and latency

Cost per test appears only where the benchmark reports it for both models. Latency is the measured completion time for that benchmark.

Benchmark Grok 4.6 cost MiMo V2.6 Flash cost Grok 4.6 latency MiMo V2.6 Flash latency
Vals Science Index $2.45 $0.12 40m10s 1h41m
Legal Research Bench $1.53 $0.07 25m04s 15m20s
Tax Agent Bench $0.98 $0.05 10m58s 17m19s
MedCode N/A N/A 2m07s 93.37s
MedScribe N/A N/A 70.94s 74.48s
ProofBench v1.1 $0.82 $0.12 14m22s 1h03m
BioMysteryBench $1.23 $0.05 14m18s 28m28s
MysteryMechanism $1.31 $0.06 27m55s 35m08s
Terminal-Bench-Science $4.82 $0.24 1h18m 3h59m
IOI $8.18 $0.22 3h57m 1h49m
ProgramBench $16.76 $0.47 4h27m 3h22m
Terminal-Bench 4.0 $5.06 $0.21 29m25s 2h25m
Vibe Code Bench v1.1 $4.88 $0.56 25m30s 50m13s
CyberBench v1.1 $4.07 $0.05 36m52s 28m22s
Access to Justice Benchmark $0.71 $0.02 6m13s 12m34s
Public Benefits Bench v1.1 $0.92 $0.03 25m53s 20m56s

Results available only for Grok 4.6

  • Vals RSI Index
  • Immigration
  • LegalBench
  • MortgageTax
  • TaxEval v2
  • GPQA Diamond
  • MMLU Pro
  • LiveCodeBench
  • SkillsBench
  • SWE-bench
  • Time Horizon Index: KSP

Results available only for MiMo V2.6 Flash

  • Vals Index
  • Vals Finance Index
  • Vals Legal Index
  • HLAB-Vals-1.1
  • EMB v1.1
  • Finance Agent v2.1
  • SAGE
  • Code Migration v1.1
  • Vibe Code Bench 1-100 v1.1
  • SRE Bench
Model details Grok 4.6 Model details MiMo V2.6 Flash