Grok 4.6 vs GPT-5.6 Terra: Benchmark Comparison
Grok 4.6 has the higher score on 13 of 20 shared benchmarks; GPT-5.6 Terra leads on 7.
The largest observed score gap is 40.00 pts on IOI , where GPT-5.6 Terra leads.
Reported ±1 standard-error ranges overlap on 10 of 20 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 4.6 | GPT-5.6 Terra | Gap | Reported uncertainty |
|---|---|---|---|---|
| Legal Research Bench | 48.08% ±3.47 | 41.35% ±3.42 | 6.73 pts | Reported ±1 SE ranges overlap |
| LegalBench | 86.31% ±0.42 | 85.11% ±0.45 | 1.20 pts | Reported ±1 SE ranges do not overlap |
| MortgageTax | 64.19% ±0.95 | 67.33% ±0.93 | 3.14 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 33.66% ±3.41 | 30.04% ±3.31 | 3.62 pts | Reported ±1 SE ranges overlap |
| TaxEval v2 | 71.10% ±0.90 | 76.17% ±0.84 | 5.07 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 44.71% ±2.26 | 43.41% ±2.17 | 1.30 pts | Reported ±1 SE ranges overlap |
| MedScribe | 86.53% ±1.96 | 82.87% ±1.95 | 3.67 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 51.00% ±5.02 | 74.00% ±4.41 | 23.00 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench-Science | 11.43% ±3.83 | 10.00% ±3.61 | 1.43 pts | Reported ±1 SE ranges overlap |
| GPQA Diamond | 94.70% ±1.13 | 90.91% ±1.91 | 3.79 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 89.40% ±0.30 | 86.66% ±0.33 | 2.74 pts | Reported ±1 SE ranges do not overlap |
| IOI | 47.61% ±2.09 | 87.61% ±6.53 | 40.00 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 88.22% ±0.94 | 85.93% ±1.02 | 2.29 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 1.00% ±0.70 | 0.50% ±0.50 | 0.50 pts | Reported ±1 SE ranges overlap |
| SkillsBench | 55.77% ±4.84 | 58.90% ±4.47 | 3.13 pts | Reported ±1 SE ranges overlap |
| SWE-bench | 95.60% ±0.92 | 95.40% ±0.94 | 0.20 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench 4.0 | 17.17% ±1.34 | 22.73% ±2.31 | 5.55 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 76.24% ±3.82 | 74.59% ±4.20 | 1.65 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 67.68% ±5.87 | 72.08% ±5.41 | 4.41 pts | Reported ±1 SE ranges overlap |
| Public Benefits Bench v1.1 | 66.85% ±1.23 | 62.38% ±1.26 | 4.46 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Grok 4.6 average | GPT-5.6 Terra average |
|---|---|---|
| Legal | 67.19% | 63.23% |
| Finance | 56.31% | 57.84% |
| Healthcare | 65.62% | 63.14% |
| Math | 51.00% | 74.00% |
| Science | 11.43% | 10.00% |
| Academic | 92.05% | 88.78% |
| Coding | 54.52% | 60.81% |
| Cyber | 67.68% | 72.08% |
| Social Mobility | 66.85% | 62.38% |
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 4.6 cost | GPT-5.6 Terra cost | Grok 4.6 latency | GPT-5.6 Terra latency |
|---|---|---|---|---|
| Legal Research Bench | $1.53 | $7.91 | 25m04s | 1h10m |
| LegalBench | N/A | N/A | 27.42s | 2.78s |
| MortgageTax | N/A | N/A | 8.55s | 6.32s |
| Tax Agent Bench | $0.98 | $4.83 | 10m58s | 1h01m |
| TaxEval v2 | N/A | N/A | 47.57s | 37.28s |
| MedCode | N/A | N/A | 2m07s | 18.41s |
| MedScribe | N/A | N/A | 70.94s | 35.53s |
| ProofBench v1.1 | $0.82 | $1.27 | 14m22s | 12m57s |
| Terminal-Bench-Science | $4.82 | $5.19 | 1h18m | 2h04m |
| GPQA Diamond | N/A | N/A | 3m29s | 36.76s |
| MMLU Pro | N/A | N/A | 54.98s | 8.17s |
| IOI | $8.18 | $8.66 | 3h57m | 1h23m |
| LiveCodeBench | N/A | N/A | 118.40s | 44.33s |
| ProgramBench | $16.76 | $5.38 | 4h27m | 33m36s |
| SkillsBench | $0.92 | $1.75 | 13m28s | 6m55s |
| SWE-bench | $0.78 | $0.40 | 10m04s | 3m00s |
| Terminal-Bench 4.0 | $5.06 | $5.60 | 29m25s | 31m29s |
| Vibe Code Bench v1.1 | $4.88 | $7.89 | 25m30s | 19m12s |
| CyberBench v1.1 | $4.07 | $3.31 | 36m52s | 17m04s |
| Public Benefits Bench v1.1 | $0.92 | $1.20 | 25m53s | 19m31s |
Results available only for Grok 4.6
- Vals RSI Index
- Vals Science Index
- Immigration
- BioMysteryBench
- MysteryMechanism
- Access to Justice Benchmark
- Time Horizon Index: KSP
Results available only for GPT-5.6 Terra
- MMMU Pro
- SAGE
- SRE Bench
- Financial Coaching Bench