Grok 4.7 vs GLM 5.3: Benchmark Comparison
Grok 4.7 has the higher score on 7 of 23 shared benchmarks; GLM 5.3 leads on 16.
The largest observed score gap is 23.00 pts on ProofBench v1.1 , where GLM 5.3 leads.
Reported ±1 standard-error ranges overlap on 14 of 22 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 | GLM 5.3 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Finance Index | 58.46% ±1.45 | 60.54% ±1.52 | 2.08 pts | Reported ±1 SE ranges overlap |
| Vals Index | 58.56% ±1.01 | 59.73% ±1.11 | 1.16 pts | Reported ±1 SE ranges overlap |
| Vals Legal Index | 72.60% ±1.82 | 74.58% ±1.84 | 1.98 pts | Reported ±1 SE ranges overlap |
| Vals RSI Index | 20.20% | 22.91% | 2.71 pts | Uncertainty comparison unavailable |
| HLAB-Vals-1.1 | 18.33% ±3.18 | 14.58% ±2.86 | 3.75 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 |
| LegalBench | 84.39% ±0.46 | 84.84% ±0.40 | 0.45 pts | Reported ±1 SE ranges overlap |
| EMB v1.1 | 71.50% ±2.33 | 69.11% ±2.65 | 2.39 pts | Reported ±1 SE ranges overlap |
| Finance Agent v2.1 | 60.59% ±2.11 | 65.00% ±2.01 | 4.42 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 34.20% ±3.42 | 39.70% ±3.52 | 5.50 pts | Reported ±1 SE ranges overlap |
| MedCode | 49.55% ±2.17 | 42.86% ±2.11 | 6.69 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 89.38% ±1.89 | 88.81% ±2.00 | 0.57 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 26.00% ±4.41 | 49.00% ±5.02 | 23.00 pts | Reported ±1 SE ranges do not overlap |
| MysteryMechanism | 25.23% ±2.92 | 22.97% ±2.83 | 2.25 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench-Science | 10.00% ±3.61 | 5.71% ±2.79 | 4.29 pts | Reported ±1 SE ranges overlap |
| Code Migration v1.1 | 53.22% ±2.56 | 55.07% ±2.12 | 1.86 pts | Reported ±1 SE ranges overlap |
| IOI | 57.72% ±1.99 | 68.44% ±7.48 | 10.72 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 | 28.79% ±2.31 | 38.89% ±1.82 | 10.10 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 86.17% ±2.18 | 78.13% ±3.94 | 8.05 pts | Reported ±1 SE ranges do not overlap |
| CyberBench v1.1 | 69.46% ±5.67 | 72.08% ±5.41 | 2.62 pts | Reported ±1 SE ranges overlap |
| SRE Bench | 3.82% ±1.19 | 9.16% ±1.79 | 5.34 pts | Reported ±1 SE ranges do not overlap |
| Public Benefits Bench v1.1 | 65.63% ±1.24 | 68.54% ±1.21 | 2.91 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Grok 4.7 average | GLM 5.3 average |
|---|---|---|
| Legal | 49.95% | 49.49% |
| Finance | 55.43% | 57.94% |
| Healthcare | 69.47% | 65.84% |
| Math | 26.00% | 49.00% |
| Science | 17.61% | 14.34% |
| Coding | 45.28% | 48.41% |
| Cyber | 36.64% | 40.62% |
| Social Mobility | 65.63% | 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 | Grok 4.7 cost | GLM 5.3 cost | Grok 4.7 latency | GLM 5.3 latency |
|---|---|---|---|---|
| Vals Finance Index | $3.51 | $2.21 | 20m49s | 35m44s |
| Vals Index | $11.63 | $8.52 | 33m34s | 1h04m |
| Vals Legal Index | $5.82 | $2.68 | 24m33s | 44m51s |
| Vals RSI Index | $237.12 | $61.84 | 90h00m | 90h00m |
| HLAB-Vals-1.1 | $10.75 | $3.99 | 35m48s | 31m51s |
| Legal Research Bench | $4.92 | $2.24 | 21m14s | 51m50s |
| LegalBench | N/A | N/A | 26.02s | 22.48s |
| EMB v1.1 | $6.48 | $3.79 | 34m57s | 36m12s |
| Finance Agent v2.1 | $2.24 | $1.03 | 10m52s | 20m06s |
| Tax Agent Bench | $1.80 | $1.80 | 16m36s | 50m53s |
| MedCode | N/A | N/A | 3m33s | 2m49s |
| MedScribe | N/A | N/A | 2m33s | 2m02s |
| ProofBench v1.1 | $0.79 | $2.08 | 12m47s | 42m23s |
| MysteryMechanism | $1.84 | $1.53 | 17m33s | 30m42s |
| Terminal-Bench-Science | $17.04 | $15.63 | 1h33m | 2h45m |
| Code Migration v1.1 | $38.05 | $34.91 | 1h05m | 2h58m |
| IOI | $12.71 | $7.67 | 46m48s | 1h46m |
| ProgramBench | $46.49 | $21.96 | 3h38m | 4h16m |
| Terminal-Bench 4.0 | $18.01 | $9.37 | 50m08s | 1h23m |
| Vibe Code Bench v1.1 | $15.83 | $12.45 | 35m47s | 1h04m |
| CyberBench v1.1 | $8.54 | $2.69 | 15m30s | 30m18s |
| SRE Bench | $64.77 | $27.47 | 1h41m | 2h48m |
| Public Benefits Bench v1.1 | $2.25 | $0.95 | 16m57s | 35m51s |
Results available only for Grok 4.7
- Vals Science Index
- BioMysteryBench
- Robo-bench
- SAGE
- SWE-bench Multimodal
Results available only for GLM 5.3
- TaxEval v2
- GPQA Diamond
- MMLU Pro
- LiveCodeBench
- SkillsBench
- SWE-bench
- Vibe Code Bench 1-100