MiMo V2.6 Pro vs GLM 5.3: Benchmark Comparison
MiMo V2.6 Pro has the higher score on 5 of 21 shared benchmarks; GLM 5.3 leads on 16.
The largest observed score gap is 29.11 pts on IOI , where GLM 5.3 leads.
Reported ±1 standard-error ranges overlap on 14 of 21 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 | MiMo V2.6 Pro | GLM 5.3 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Finance Index | 57.85% ±1.57 | 60.54% ±1.52 | 2.70 pts | Reported ±1 SE ranges overlap |
| Vals Index | 57.81% ±1.24 | 59.73% ±1.11 | 1.92 pts | Reported ±1 SE ranges overlap |
| Vals Legal Index | 72.14% ±1.83 | 74.58% ±1.84 | 2.43 pts | Reported ±1 SE ranges overlap |
| HLAB-Vals-1.1 | 13.75% ±2.84 | 14.58% ±2.86 | 0.83 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 47.12% ±3.47 | 49.04% ±3.48 | 1.92 pts | Reported ±1 SE ranges overlap |
| EMB v1.1 | 67.35% ±2.90 | 69.11% ±2.65 | 1.77 pts | Reported ±1 SE ranges overlap |
| Finance Agent v2.1 | 64.26% ±2.02 | 65.00% ±2.01 | 0.75 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 32.39% ±3.36 | 39.70% ±3.52 | 7.31 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 44.97% ±2.10 | 42.86% ±2.11 | 2.11 pts | Reported ±1 SE ranges overlap |
| MedScribe | 88.31% ±1.94 | 88.81% ±2.00 | 0.50 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 70.00% ±4.61 | 49.00% ±5.02 | 21.00 pts | Reported ±1 SE ranges do not overlap |
| MysteryMechanism | 15.31% ±2.42 | 22.97% ±2.83 | 7.66 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench-Science | 2.86% ±2.01 | 5.71% ±2.79 | 2.86 pts | Reported ±1 SE ranges overlap |
| Code Migration v1.1 | 48.79% ±3.88 | 55.07% ±2.12 | 6.29 pts | Reported ±1 SE ranges do not overlap |
| IOI | 39.33% ±2.41 | 68.44% ±7.48 | 29.11 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 0.50% ±0.50 | 1.50% ±0.86 | 1.00 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench 4.0 | 31.31% ±3.07 | 38.89% ±1.82 | 7.58 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 85.22% ±3.39 | 78.13% ±3.94 | 7.10 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 72.86% ±5.50 | 72.08% ±5.41 | 0.77 pts | Reported ±1 SE ranges overlap |
| SRE Bench | 3.05% ±1.06 | 9.16% ±1.79 | 6.11 pts | Reported ±1 SE ranges do not overlap |
| Public Benefits Bench v1.1 | 68.94% ±1.20 | 68.54% ±1.21 | 0.41 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | MiMo V2.6 Pro average | GLM 5.3 average |
|---|---|---|
| Legal | 30.43% | 31.81% |
| Finance | 54.66% | 57.94% |
| Healthcare | 66.64% | 65.84% |
| Math | 70.00% | 49.00% |
| Science | 9.09% | 14.34% |
| Coding | 41.03% | 48.41% |
| Cyber | 37.95% | 40.62% |
| Social Mobility | 68.94% | 68.54% |
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 | MiMo V2.6 Pro cost | GLM 5.3 cost | MiMo V2.6 Pro latency | GLM 5.3 latency |
|---|---|---|---|---|
| Vals Finance Index | $0.22 | $2.21 | 30m48s | 35m44s |
| Vals Index | $0.43 | $8.52 | 1h13m | 1h04m |
| Vals Legal Index | $0.18 | $2.68 | 29m02s | 44m51s |
| HLAB-Vals-1.1 | $0.22 | $3.99 | 31m02s | 31m51s |
| Legal Research Bench | $0.18 | $2.24 | 30m16s | 51m50s |
| EMB v1.1 | $0.33 | $3.79 | 55m14s | 36m12s |
| Finance Agent v2.1 | $0.18 | $1.03 | 11m22s | 20m06s |
| Tax Agent Bench | $0.13 | $1.80 | 25m48s | 50m53s |
| MedCode | N/A | N/A | 2m57s | 2m49s |
| MedScribe | N/A | N/A | 2m53s | 2m02s |
| ProofBench v1.1 | $0.25 | $2.08 | 1h02m | 42m23s |
| MysteryMechanism | $0.15 | $1.53 | 44m00s | 30m42s |
| Terminal-Bench-Science | $0.62 | $15.63 | 3h12m | 2h45m |
| Code Migration v1.1 | $0.99 | $34.91 | 3h28m | 2h58m |
| IOI | $0.84 | $7.67 | 2h26m | 1h46m |
| ProgramBench | $0.73 | $21.96 | 3h00m | 4h16m |
| Terminal-Bench 4.0 | $0.50 | $9.37 | 2h42m | 1h23m |
| Vibe Code Bench v1.1 | $1.04 | $12.45 | 1h01m | 1h04m |
| CyberBench v1.1 | $0.09 | $2.69 | 27m41s | 30m18s |
| SRE Bench | $0.53 | $27.47 | 2h23m | 2h48m |
| Public Benefits Bench v1.1 | $0.08 | $0.95 | 37m14s | 35m51s |
Results available only for MiMo V2.6 Pro
- SAGE
- SWE-bench Multimodal
Results available only for GLM 5.3
- Vals RSI Index
- LegalBench
- TaxEval v2
- GPQA Diamond
- MMLU Pro
- LiveCodeBench
- SkillsBench
- SWE-bench
- Vibe Code Bench 1-100