Gemini 3.1 Pro Preview (02/26) vs Inkling: Benchmark Comparison
Gemini 3.1 Pro Preview (02/26) has the higher score on 16 of 25 shared benchmarks; Inkling leads on 8.
The largest observed score gap is 36.89 pts on IOI , where Gemini 3.1 Pro Preview (02/26) leads.
Reported ±1 standard-error ranges overlap on 5 of 25 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 3.1 Pro Preview (02/26) | Inkling | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 33.44% ±1.13 | 28.67% ±1.10 | 4.77 pts | Reported ±1 SE ranges do not overlap |
| Harvey's Legal Agent Benchmark | 0.00% ±0.00 | 2.08% ±0.83 | 2.08 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 20.67% ±2.81 | 28.36% ±3.13 | 7.69 pts | Reported ±1 SE ranges do not overlap |
| LegalBench | 87.40% ±0.33 | 82.95% ±0.50 | 4.45 pts | Reported ±1 SE ranges do not overlap |
| EMB | 52.62% ±2.97 | 38.36% ±3.27 | 14.25 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 42.98% ±1.21 | 46.60% ±0.93 | 3.62 pts | Reported ±1 SE ranges do not overlap |
| MortgageTax | 69.40% ±0.91 | 63.99% ±0.94 | 5.41 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 37.84% ±3.10 | 43.52% ±2.95 | 5.67 pts | Reported ±1 SE ranges overlap |
| TaxEval v2 | 72.88% ±0.86 | 75.31% ±0.84 | 2.42 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 59.06% ±2.00 | 41.19% ±2.23 | 17.87 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 76.11% ±1.92 | 85.41% ±1.84 | 9.29 pts | Reported ±1 SE ranges do not overlap |
| ProofBench v1.1 | 26.00% ±4.41 | 0.00% ±0.00 | 26.00 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 95.45% ±1.05 | 87.12% ±1.78 | 8.33 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 90.99% ±0.28 | 86.30% ±0.34 | 4.69 pts | Reported ±1 SE ranges do not overlap |
| MMMU Pro | 88.21% ±0.78 | 78.50% ±0.99 | 9.71 pts | Reported ±1 SE ranges do not overlap |
| SAGE | 48.68% ±3.29 | 36.55% ±3.22 | 12.12 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 17.31% ±3.93 | 11.79% ±3.40 | 5.52 pts | Reported ±1 SE ranges overlap |
| IOI | 51.83% ±2.59 | 14.94% ±5.40 | 36.89 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 88.48% ±0.93 | 85.52% ±1.00 | 2.97 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 |
| SWE-bench | 78.80% ±1.83 | 77.60% ±1.87 | 1.20 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench 4.0 | 2.52% ±0.51 | 0.51% ±0.51 | 2.02 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench 1-100 | 6.69% ±2.40 | 7.33% ±1.84 | 0.64 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 32.03% ±4.34 | 19.21% ±3.66 | 12.82 pts | Reported ±1 SE ranges do not overlap |
| Public Benefits Bench v1.1 | 53.79% ±1.30 | 58.46% ±1.28 | 4.67 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Gemini 3.1 Pro Preview (02/26) average | Inkling average |
|---|---|---|
| Legal | 36.02% | 37.80% |
| Finance | 55.14% | 53.55% |
| Healthcare | 67.59% | 63.30% |
| Math | 26.00% | 0.00% |
| Academic | 91.55% | 83.97% |
| Education | 48.68% | 36.55% |
| Coding | 34.71% | 27.11% |
| Social Mobility | 53.79% | 58.46% |
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 3.1 Pro Preview (02/26) cost | Inkling cost | Gemini 3.1 Pro Preview (02/26) latency | Inkling latency |
|---|---|---|---|---|
| Vals Index | $2.18 | $1.46 | 9m52s | 20m06s |
| Harvey's Legal Agent Benchmark | $1.15 | $1.25 | 7m17s | 18m24s |
| Legal Research Bench | $1.10 | $0.49 | 4m02s | 14m29s |
| LegalBench | N/A | N/A | 10.06s | 23.14s |
| EMB | $3.77 | $1.67 | 11m49s | 26m22s |
| Finance Agent (v2) | $1.59 | $1.00 | 3m28s | 18m02s |
| MortgageTax | N/A | N/A | 23.62s | 69.11s |
| Tax Agent Bench | $0.30 | $0.35 | 100.96s | 13m31s |
| TaxEval v2 | N/A | N/A | 41.93s | 3m18s |
| MedCode | N/A | N/A | 38.52s | 2m47s |
| MedScribe | N/A | N/A | 69.14s | 4m05s |
| ProofBench v1.1 | $0.78 | $0.20 | 14m49s | 7m16s |
| GPQA Diamond | N/A | N/A | 65.76s | 5m09s |
| MMLU Pro | N/A | N/A | 23.91s | 73.26s |
| MMMU Pro | N/A | N/A | 76.99s | 2m04s |
| SAGE | N/A | N/A | 61.17s | 3m18s |
| Code Migration | $1.61 | $3.01 | 12m01s | 29m34s |
| IOI | $1.25 | $1.71 | 12m03s | 30m12s |
| LiveCodeBench | N/A | N/A | 88.89s | 4m18s |
| ProgramBench | $2.63 | $4.14 | 12m36s | 45m34s |
| SWE-bench | $0.78 | $0.59 | 5m12s | 6m34s |
| Terminal-Bench 4.0 | $4.11 | $2.51 | 18m44s | 22m52s |
| Vibe Code Bench 1-100 | $3.36 | $5.00 | 11m28s | 50m02s |
| Vibe Code Bench v1.1 | $3.83 | $1.61 | 20m12s | 18m25s |
| Public Benefits Bench v1.1 | $0.38 | $0.37 | 3m06s | 13m31s |
Results available only for Gemini 3.1 Pro Preview (02/26)
- BioMysteryBench
- MysteryMechanism
- Terminal-Bench Science
Results available only for Inkling
- SkillsBench
- CyberBench v1.1