Ember-1 vs Hy4 Preview: Benchmark Comparison
Ember-1 has the higher score on 4 of 10 shared benchmarks; Hy4 Preview leads on 6.
The largest observed score gap is 14.00 pts on ProofBench v1.1 , where Hy4 Preview leads.
Reported ±1 standard-error ranges overlap on 7 of 10 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 | Ember-1 | Hy4 Preview | Gap | Reported uncertainty |
|---|---|---|---|---|
| Legal Research Bench | 44.71% ±3.46 | 45.19% ±3.46 | 0.48 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 31.08% ±3.34 | 32.62% ±3.38 | 1.54 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 61.00% ±4.90 | 75.00% ±4.35 | 14.00 pts | Reported ±1 SE ranges do not overlap |
| BioMysteryBench | 67.04% ±3.03 | 69.26% ±2.59 | 2.22 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench-Science | 5.71% ±2.79 | 1.43% ±1.43 | 4.29 pts | Reported ±1 SE ranges do not overlap |
| IOI | 46.33% ±9.16 | 59.33% ±4.60 | 13.00 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench 4.0 | 20.71% ±3.64 | 8.08% ±1.34 | 12.63 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 83.87% ±3.15 | 77.48% ±4.04 | 6.39 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 69.52% ±5.56 | 65.36% ±5.55 | 4.17 pts | Reported ±1 SE ranges overlap |
| Public Benefits Bench v1.1 | 66.17% ±1.23 | 68.61% ±1.21 | 2.43 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Ember-1 average | Hy4 Preview average |
|---|---|---|
| Legal | 44.71% | 45.19% |
| Finance | 31.08% | 32.62% |
| Math | 61.00% | 75.00% |
| Science | 36.38% | 35.34% |
| Coding | 50.30% | 48.30% |
| Cyber | 69.52% | 65.36% |
| Social Mobility | 66.17% | 68.61% |
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 | Ember-1 cost | Hy4 Preview cost | Ember-1 latency | Hy4 Preview latency |
|---|---|---|---|---|
| Legal Research Bench | $3.67 | $0.85 | 38m34s | 1h04m |
| Tax Agent Bench | $2.97 | $0.59 | 30m46s | 41m04s |
| ProofBench v1.1 | $1.74 | $0.34 | 21m09s | 22m54s |
| BioMysteryBench | $0.91 | $0.36 | 9m26s | 23m30s |
| Terminal-Bench-Science | $30.76 | $2.14 | 3h23m | 3h48m |
| IOI | $24.46 | $1.35 | 1h47m | 1h01m |
| Terminal-Bench 4.0 | $19.48 | $2.10 | 1h55m | 2h10m |
| Vibe Code Bench v1.1 | $8.56 | $2.18 | 39m18s | 41m33s |
| CyberBench v1.1 | $2.43 | $0.49 | 22m02s | 36m43s |
| Public Benefits Bench v1.1 | $1.02 | $0.25 | 13m21s | 1h03m |
Results available only for Ember-1
- Vals Science Index
- MysteryMechanism
Results available only for Hy4 Preview
- Vals Finance Index
- Vals Index
- Vals Legal Index
- HLAB-Vals-1.1
- LegalBench
- EMB v1.1
- Finance Agent v2.1
- MedCode
- MedScribe
- Code Migration v1.1
- ProgramBench
- SRE Bench