Grok 4.7 vs MiMo V2.6 Pro: Benchmark Comparison
Grok 4.7 has the higher score on 10 of 19 shared benchmarks; MiMo V2.6 Pro leads on 7.
The largest observed score gap is 44.00 pts on ProofBench v1.1 , where MiMo V2.6 Pro leads.
Reported ±1 standard-error ranges overlap on 12 of 19 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 Pro | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 54.95% ±1.07 | 55.20% ±1.18 | 0.25 pts | Reported ±1 SE ranges overlap |
| Harvey's Legal Agent Benchmark | 12.50% ±2.66 | 10.83% ±2.45 | 1.67 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 47.12% ±3.47 | 47.12% ±3.47 | 0.00 pts | Reported ±1 SE ranges overlap |
| EMB | 66.99% ±3.04 | 62.86% ±3.14 | 4.13 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 52.25% ±0.35 | 57.34% ±0.57 | 5.09 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 65.60% ±3.24 | 64.94% ±3.21 | 0.66 pts | Reported ±1 SE ranges overlap |
| MedCode | 49.55% ±2.17 | 44.97% ±2.10 | 4.58 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 89.38% ±1.89 | 88.31% ±1.94 | 1.07 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 26.00% ±4.41 | 70.00% ±4.61 | 44.00 pts | Reported ±1 SE ranges do not overlap |
| MysteryMechanism | 25.23% ±2.92 | 15.31% ±2.42 | 9.91 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench Science | 10.00% ±3.61 | 2.86% ±2.01 | 7.14 pts | Reported ±1 SE ranges do not overlap |
| SAGE | 40.79% ±3.35 | 45.05% ±3.40 | 4.26 pts | Reported ±1 SE ranges overlap |
| Code Migration | 44.82% ±4.21 | 43.01% ±4.32 | 1.80 pts | Reported ±1 SE ranges overlap |
| IOI | 57.72% ±1.99 | 39.33% ±2.41 | 18.39 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 | 31.31% ±3.07 | 2.52 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 86.17% ±2.18 | 85.22% ±3.39 | 0.95 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 69.46% ±5.67 | 72.86% ±5.50 | 3.39 pts | Reported ±1 SE ranges overlap |
| Public Benefits Bench v1.1 | 65.63% ±1.24 | 68.94% ±1.20 | 3.32 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Grok 4.7 average | MiMo V2.6 Pro average |
|---|---|---|
| Legal | 29.81% | 28.97% |
| Finance | 61.61% | 61.71% |
| Healthcare | 69.47% | 66.64% |
| Math | 26.00% | 70.00% |
| Science | 17.61% | 9.09% |
| Education | 40.79% | 45.05% |
| Coding | 43.60% | 39.88% |
| Cyber | 69.46% | 72.86% |
| Social Mobility | 65.63% | 68.94% |
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 Pro cost | Grok 4.7 latency | MiMo V2.6 Pro latency |
|---|---|---|---|---|
| Vals Index | $12.12 | $0.41 | 35m31s | 1h07m |
| Harvey's Legal Agent Benchmark | $11.13 | $0.22 | 42m05s | 25m49s |
| Legal Research Bench | $4.92 | $0.18 | 21m14s | 30m16s |
| EMB | $6.48 | $0.33 | 34m57s | 55m14s |
| Finance Agent (v2) | $2.72 | $0.20 | 15m33s | 10m48s |
| Tax Agent Bench | $1.80 | $0.13 | 16m36s | 25m48s |
| MedCode | N/A | N/A | 3m33s | 2m57s |
| MedScribe | N/A | N/A | 2m33s | 2m53s |
| ProofBench v1.1 | $0.79 | $0.25 | 12m47s | 1h02m |
| MysteryMechanism | $1.84 | $0.15 | 17m33s | 44m00s |
| Terminal-Bench Science | $14.45 | $0.62 | 1h29m | 3h12m |
| SAGE | N/A | N/A | 4m51s | 3m40s |
| Code Migration | $36.55 | $0.69 | 1h09m | 2h49m |
| IOI | $12.71 | $0.84 | 46m48s | 2h26m |
| ProgramBench | $46.49 | $0.73 | 3h38m | 3h00m |
| Terminal-Bench 4.0 | $18.09 | $0.50 | 50m21s | 2h42m |
| Vibe Code Bench v1.1 | $15.83 | $1.04 | 35m47s | 1h01m |
| CyberBench v1.1 | $8.54 | $0.09 | 15m30s | 27m41s |
| Public Benefits Bench v1.1 | $2.25 | $0.08 | 16m57s | 37m14s |
Results available only for Grok 4.7
- Vals RSI Index
- LegalBench
- BioMysteryBench
Results available only for MiMo V2.6 Pro
- SRE Bench