Grok 4.7 vs GPT-5.6 Sol: Benchmark Comparison
Grok 4.7 has the higher score on 4 of 19 shared benchmarks; GPT-5.6 Sol leads on 15.
The largest observed score gap is 57.00 pts on ProofBench v1.1 , where GPT-5.6 Sol leads.
Reported ±1 standard-error ranges overlap on 7 of 18 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 | GPT-5.6 Sol | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals RSI Index | 20.20% | 23.88% | 3.68 pts | Uncertainty comparison unavailable |
| Vals Science Index | 34.83% ±1.61 | 41.48% ±1.93 | 6.65 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 47.12% ±3.47 | 48.08% ±3.47 | 0.96 pts | Reported ±1 SE ranges overlap |
| LegalBench | 84.39% ±0.46 | 86.97% ±0.41 | 2.58 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 34.20% ±3.42 | 31.09% ±3.34 | 3.11 pts | Reported ±1 SE ranges overlap |
| MedCode | 49.55% ±2.17 | 43.97% ±2.26 | 5.58 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 89.38% ±1.89 | 85.23% ±1.97 | 4.14 pts | Reported ±1 SE ranges do not overlap |
| ProofBench v1.1 | 26.00% ±4.41 | 83.00% ±3.77 | 57.00 pts | Reported ±1 SE ranges do not overlap |
| BioMysteryBench | 69.26% ±1.33 | 71.11% ±0.64 | 1.85 pts | Reported ±1 SE ranges overlap |
| MysteryMechanism | 25.23% ±2.92 | 33.33% ±3.17 | 8.11 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench-Science | 10.00% ±3.61 | 20.00% ±4.82 | 10.00 pts | Reported ±1 SE ranges do not overlap |
| SAGE | 40.79% ±3.35 | 52.56% ±3.42 | 11.77 pts | Reported ±1 SE ranges do not overlap |
| IOI | 57.72% ±1.99 | 91.17% ±4.51 | 33.45 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 | 37.88% ±0.00 | 9.09 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 86.17% ±2.18 | 80.50% ±3.72 | 5.68 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 69.46% ±5.67 | 76.31% ±5.18 | 6.85 pts | Reported ±1 SE ranges overlap |
| SRE Bench | 3.82% ±1.19 | 30.53% ±2.85 | 26.72 pts | Reported ±1 SE ranges do not overlap |
| Public Benefits Bench v1.1 | 65.63% ±1.24 | 66.51% ±1.23 | 0.88 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Grok 4.7 average | GPT-5.6 Sol average |
|---|---|---|
| Legal | 65.75% | 67.52% |
| Finance | 34.20% | 31.09% |
| Healthcare | 69.47% | 64.60% |
| Math | 26.00% | 83.00% |
| Science | 34.83% | 41.48% |
| Education | 40.79% | 52.56% |
| Coding | 43.30% | 52.76% |
| Cyber | 36.64% | 53.42% |
| Social Mobility | 65.63% | 66.51% |
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 | GPT-5.6 Sol cost | Grok 4.7 latency | GPT-5.6 Sol latency |
|---|---|---|---|---|
| Vals RSI Index | $237.12 | $347.10 | 90h00m | 90h00m |
| Vals Science Index | $7.12 | $3.40 | 40m34s | 43m32s |
| Legal Research Bench | $4.92 | $21.61 | 21m14s | 1h17m |
| LegalBench | N/A | N/A | 26.02s | 6.20s |
| Tax Agent Bench | $1.80 | $7.51 | 16m36s | 44m41s |
| MedCode | N/A | N/A | 3m33s | 96.59s |
| MedScribe | N/A | N/A | 2m33s | 94.40s |
| ProofBench v1.1 | $0.79 | $1.44 | 12m47s | 8m40s |
| BioMysteryBench | $2.49 | $1.93 | 11m37s | 18m18s |
| MysteryMechanism | $1.84 | $0.96 | 17m33s | 8m43s |
| Terminal-Bench-Science | $17.04 | $7.32 | 1h33m | 1h44m |
| SAGE | N/A | N/A | 4m51s | 75.39s |
| IOI | $12.71 | $7.98 | 46m48s | 1h02m |
| ProgramBench | $46.49 | $15.29 | 3h38m | 29m24s |
| Terminal-Bench 4.0 | $18.01 | $7.98 | 50m08s | 33m46s |
| Vibe Code Bench v1.1 | $15.83 | $33.40 | 35m47s | 33m53s |
| CyberBench v1.1 | $8.54 | $3.05 | 15m30s | 10m47s |
| SRE Bench | $64.77 | $42.52 | 1h41m | 1h28m |
| Public Benefits Bench v1.1 | $2.25 | $8.85 | 16m57s | 1h01m |
Results available only for Grok 4.7
- Vals Finance Index
- Vals Index
- Vals Legal Index
- HLAB-Vals-1.1
- EMB v1.1
- Finance Agent v2.1
- Robo-bench
- Code Migration v1.1
- SWE-bench Multimodal
Results available only for GPT-5.6 Sol
- MortgageTax
- TaxEval v2
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- LiveCodeBench
- SkillsBench
- SWE-bench
- Vibe Code Bench 1-100
- CUA-bench
- Time Horizon Index: KSP