Grok 4.7 vs MiMo V2.6 Flash: Benchmark Comparison

Grok 4.7 has the higher score on 19 of 26 shared benchmarks; MiMo V2.6 Flash leads on 5.

The largest observed score gap is 37.00 pts on ProofBench v1.1 , where MiMo V2.6 Flash leads.

Reported ±1 standard-error ranges overlap on 12 of 26 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 4.7 MiMo V2.6 Flash Gap Reported uncertainty
Vals Index 58.62% ±1.01 54.83% ±1.11 3.79 pts Reported ±1 SE ranges do not overlap
Vals Finance Index 58.83% ±1.45 57.15% ±1.39 1.68 pts Reported ±1 SE ranges overlap
Vals Legal Index 72.67% ±1.82 68.99% ±1.77 3.68 pts Reported ±1 SE ranges do not overlap
Vals Science Index 34.83% ±1.61 31.72% ±1.27 3.11 pts Reported ±1 SE ranges do not overlap
HLAB-Vals-1.1 18.33% ±3.18 13.33% ±2.82 5.00 pts Reported ±1 SE ranges overlap
Legal Research Bench 47.12% ±3.47 37.98% ±3.37 9.13 pts Reported ±1 SE ranges do not overlap
EMB v1.1 71.50% ±2.33 68.88% ±2.27 2.62 pts Reported ±1 SE ranges overlap
Finance Agent v2.1 60.59% ±2.11 63.32% ±2.08 2.73 pts Reported ±1 SE ranges overlap
Tax Agent Bench 35.75% ±3.46 28.51% ±3.14 7.24 pts Reported ±1 SE ranges do not overlap
MedCode 49.55% ±2.17 41.06% ±2.03 8.50 pts Reported ±1 SE ranges do not overlap
MedScribe 89.38% ±1.89 85.28% ±1.99 4.10 pts Reported ±1 SE ranges do not overlap
ProofBench v1.1 26.00% ±4.41 63.00% ±4.85 37.00 pts Reported ±1 SE ranges do not overlap
BioMysteryBench 69.26% ±1.33 69.26% ±0.98 0.00 pts Reported ±1 SE ranges overlap
MysteryMechanism 25.23% ±2.92 21.62% ±2.77 3.60 pts Reported ±1 SE ranges overlap
Terminal-Bench-Science 10.00% ±3.61 4.29% ±2.44 5.71 pts Reported ±1 SE ranges overlap
SAGE 88.70% ±1.81 83.26% ±2.14 5.45 pts Reported ±1 SE ranges do not overlap
Code Migration v1.1 53.22% ±2.56 39.55% ±3.54 13.66 pts Reported ±1 SE ranges do not overlap
IOI 57.72% ±1.99 47.67% ±4.79 10.05 pts Reported ±1 SE ranges do not overlap
ProgramBench 0.50% ±0.50 0.50% ±0.50 0.00 pts Reported ±1 SE ranges overlap
Terminal-Bench 4.0 28.79% ±2.31 24.24% ±1.51 4.55 pts Reported ±1 SE ranges do not overlap
Vibe Code Bench 1-100 v1.1 26.35% ±4.22 24.50% ±4.06 1.85 pts Reported ±1 SE ranges overlap
Vibe Code Bench v1.1 86.17% ±2.18 78.96% ±4.04 7.22 pts Reported ±1 SE ranges do not overlap
CyberBench v1.1 69.46% ±5.67 75.36% ±5.42 5.89 pts Reported ±1 SE ranges overlap
SRE Bench 3.82% ±1.19 4.20% ±1.24 0.38 pts Reported ±1 SE ranges overlap
Access to Justice Benchmark 73.69% ±0.71 70.75% ±0.73 2.94 pts Reported ±1 SE ranges do not overlap
Public Benefits Bench v1.1 65.63% ±1.24 67.59% ±1.22 1.96 pts Reported ±1 SE ranges overlap

Performance by category

Category Grok 4.7 average MiMo V2.6 Flash average
Legal 32.72% 25.66%
Finance 55.94% 53.57%
Healthcare 69.47% 63.17%
Math 26.00% 63.00%
Science 34.83% 31.72%
Education 88.70% 83.26%
Coding 42.13% 35.90%
Cyber 36.64% 39.78%
Social Mobility 69.66% 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 4.7 cost MiMo V2.6 Flash cost Grok 4.7 latency MiMo V2.6 Flash latency
Vals Index $11.63 $0.22 33m34s 1h07m
Vals Finance Index $3.51 $0.07 20m49s 19m26s
Vals Legal Index $5.82 $0.07 24m33s 18m20s
Vals Science Index $7.12 $0.12 40m34s 1h41m
HLAB-Vals-1.1 $10.75 $0.09 35m48s 22m23s
Legal Research Bench $4.92 $0.07 21m14s 15m20s
EMB v1.1 $6.48 $0.11 34m57s 25m22s
Finance Agent v2.1 $2.24 $0.07 10m52s 15m36s
Tax Agent Bench $1.80 $0.05 16m36s 17m19s
MedCode N/A N/A 3m33s 93.37s
MedScribe N/A N/A 2m33s 74.48s
ProofBench v1.1 $0.79 $0.12 12m47s 1h03m
BioMysteryBench $2.49 $0.05 11m37s 28m28s
MysteryMechanism $1.84 $0.06 17m33s 35m08s
Terminal-Bench-Science $17.04 $0.24 1h33m 3h59m
SAGE $0.11 $0.01 2m01s 2m47s
Code Migration v1.1 $38.05 $0.53 1h05m 4h10m
IOI $12.71 $0.22 46m48s 1h49m
ProgramBench $46.49 $0.47 3h38m 3h22m
Terminal-Bench 4.0 $18.01 $0.21 50m08s 2h25m
Vibe Code Bench 1-100 v1.1 $41.71 $0.44 3h38m 2h34m
Vibe Code Bench v1.1 $15.83 $0.56 35m47s 50m13s
CyberBench v1.1 $8.54 $0.05 15m30s 28m22s
SRE Bench $64.77 $0.40 1h41m 3h22m
Access to Justice Benchmark $0.82 $0.02 7m47s 12m34s
Public Benefits Bench v1.1 $2.25 $0.03 16m57s 20m56s

Results available only for Grok 4.7

  • Vals RSI Index
  • Immigration
  • LegalBench
  • Robo-bench
  • SWE-bench Multimodal
  • CyberOffense
  • Financial Coaching Bench

Results available only for MiMo V2.6 Flash

None.

Model details Grok 4.7 Model details MiMo V2.6 Flash