Gemini 3.7 Flash vs Hy4 Preview: Benchmark Comparison
Gemini 3.7 Flash has the higher score on 7 of 13 shared benchmarks; Hy4 Preview leads on 5.
The largest observed score gap is 21.61 pts on CyberBench v1.1 , where Hy4 Preview leads.
Reported ±1 standard-error ranges overlap on 4 of 13 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 | Gemini 3.7 Flash | Hy4 Preview | Gap | Reported uncertainty |
|---|---|---|---|---|
| Legal Research Bench | 34.62% ±3.31 | 45.19% ±3.46 | 10.58 pts | Reported ±1 SE ranges do not overlap |
| LegalBench | 87.26% ±0.42 | 83.76% ±0.41 | 3.50 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 22.80% ±3.03 | 32.62% ±3.38 | 9.82 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 53.39% ±2.12 | 43.25% ±2.13 | 10.14 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 83.94% ±2.00 | 83.60% ±2.06 | 0.34 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 58.00% ±4.96 | 75.00% ±4.35 | 17.00 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench-Science | 7.14% ±3.10 | 1.43% ±1.43 | 5.71 pts | Reported ±1 SE ranges do not overlap |
| IOI | 67.83% ±3.61 | 59.33% ±4.60 | 8.50 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 0.00% ±0.00 | 0.00% ±0.00 | 0.00 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench 4.0 | 12.12% ±3.03 | 8.08% ±1.34 | 4.04 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 70.39% ±4.84 | 77.48% ±4.04 | 7.08 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 43.75% ±2.21 | 65.36% ±5.55 | 21.61 pts | Reported ±1 SE ranges do not overlap |
| SRE Bench | 4.58% ±1.29 | 2.29% ±0.93 | 2.29 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Gemini 3.7 Flash average | Hy4 Preview average |
|---|---|---|
| Legal | 60.94% | 64.47% |
| Finance | 22.80% | 32.62% |
| Healthcare | 68.67% | 63.42% |
| Math | 58.00% | 75.00% |
| Science | 7.14% | 1.43% |
| Coding | 37.59% | 36.22% |
| Cyber | 24.16% | 33.82% |
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 | Gemini 3.7 Flash cost | Hy4 Preview cost | Gemini 3.7 Flash latency | Hy4 Preview latency |
|---|---|---|---|---|
| Legal Research Bench | $0.76 | $0.85 | 4m49s | 1h04m |
| LegalBench | N/A | N/A | 2.23s | 90.56s |
| Tax Agent Bench | $0.48 | $0.59 | 87.24s | 41m04s |
| MedCode | N/A | N/A | 9.16s | 6m39s |
| MedScribe | N/A | N/A | 16.82s | 5m50s |
| ProofBench v1.1 | $0.56 | $0.34 | 7m04s | 22m54s |
| Terminal-Bench-Science | $7.19 | $2.14 | 1h20m | 3h48m |
| IOI | $3.40 | $1.35 | 21m09s | 1h01m |
| ProgramBench | $7.13 | $12.81 | 21m30s | 2h10m |
| Terminal-Bench 4.0 | $8.71 | $2.10 | 1h24m | 2h10m |
| Vibe Code Bench v1.1 | $4.83 | $2.18 | 23m43s | 41m33s |
| CyberBench v1.1 | $2.15 | $0.49 | 7m34s | 36m43s |
| SRE Bench | $21.47 | $4.90 | 1h50m | 1h40m |
Results available only for Gemini 3.7 Flash
- Vals RSI Index
- MortgageTax
- TaxEval v2
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- SAGE
- LiveCodeBench
- SkillsBench
- SWE-bench
Results available only for Hy4 Preview
- Vals Finance Index
- Vals Index
- Vals Legal Index
- HLAB-Vals-1.1
- EMB v1.1
- Finance Agent v2.1
- BioMysteryBench
- Code Migration v1.1
- Public Benefits Bench v1.1